FocalFormer3D : Focusing on Hard Instance for 3D Object Detection
Open accessAbstract
False negatives (FN) in 3D object detection, e.g., missing predictions of pedestrians, vehicles, or other obstacles, can lead to potentially dangerous situations in autonomous driving. While being fatal, this issue is understudied in many current 3D detection methods. In this work, we propose Hard Instance Probing (HIP), a general pipeline that identifies FN in a multi-stage manner and guides the models to focus on excavating difficult instances. For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall. FocalFormer3D features a multi-stage query generation to discover hard objects and a box-level transformer decoder to efficiently distinguish objects from massive object candidates. Experimental results on the nuScenes and Waymo datasets validate the superior performance of FocalFormer3D. The advantage leads to strong performance on both detection and tracking, in both LiDAR and multi-modal settings. Notably, FocalFormer3D achieves a 70.5 mAP and 73.9 NDS on nuScenes detection benchmark, while the nuScenes tracking benchmark shows 72.1 AMOTA, both ranking 1st place on the nuScenes LiDAR leaderboard. Our code is available at https://github.com/NVlabs/FocalFormer3D.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Radar-camera fusion enhances motion detection by leveraging radar velocity information, with RCBEVDet++ demonstrating greater stability in dynamic scenes such as high-speed driving and urban intersections.
“In contrast, radarcamera fusion enhances motion detection by leveraging radar velocity information, with RCBEVDet++ [263] demonstrating greater stability in dynamic scenes, such as high-speed driving and urban intersections.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [263]
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 56,035 · cited 1× · see citing works
“This allows for box-level query interaction and iterative box refinements, binding the object queries with sufficient box context through RoIAlign [20, 21] on the bird’s eye view to perform relative bounding box refinements.”
MethodMicrosoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460 · cited 1× · see citing works
“Following TransFusion [4], we use a pre-trained ResNet-50 model on COCO [80] and nuIm-age [62] dataset as the image model and freeze its weights during training.”
MethodFocal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581 · cited 1× · see citing works
“Recent research [65–67] has further explored soft-sampling, such as adjusting the loss distribution to mitigate foreground-background imbalance issues.”
BackgroundHe, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137 · see citing works
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755 · cited 1× · see citing works
“The generation of multi-stage BEV features is accomplished in a cascade manner using a lightweight inversed residual block [68] between stages.”
MethodGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105 · see citing works
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285 · cited 2× · see citing works
“To enhance the efficiency of object query processing, we employ deformable attention [17] instead of computationally intensive modules such as cross attention [59] or box attention [70].”
BackgroundMethodAre we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · cited 1× · see citing works
“…detected objects ( Positive predictions) at k -th stage are We are then allowed to classify the ground-truth objects according to their assigned candidates: where an object matching metric σ ( · , · ) (e.g. Intersection over Union [60, 61] and center distance [62]) and a prede-fined threshold η .”
BackgroundPointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric SpacePreprint
Qi, C. R., Yi, L., Su, H., & Guibas, L. J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.02413 · Cited by 9,834 · cited 1× · see citing works
“…LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or predictions on the sparse representations.”
BackgroundPointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Charles, R., Su, H., Mo, K., & Guibas, L. J. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.16 · Cited by 9,767 · cited 1× · see citing works
“…LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or predictions on the sparse representations.”
BackgroundCascade R-CNN: Delving Into High Quality Object Detection
Cai, Z., & Vasconcelos, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00644 · Cited by 7,370 · cited 1× · see citing works
“Motivated by cascade-style decoder head for object detection [16–18], we propose a pipeline to probe false negative samples progressively, which signifi-cantly improves the recall rate Fig.”
MethodnuScenes: A Multimodal Dataset for Autonomous Driving
Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01164 · Cited by 7,152 · cited 3× · see citing works
“Following TransFusion [4], we use a pre-trained ResNet-50 model on COCO [80] and nuIm-age [62] dataset as the image model and freeze its weights during training.”
BackgroundMethodVoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Zhou, Y., & Tuzel, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00472 · Cited by 4,813 · cited 3× · see citing works
“The computation time is mostly taken up by the sparse convolution-based backbone network (VoxelNet [1, 22]), which takes 78ms.”
BackgroundMethodPointPillars: Fast Encoders for Object Detection From Point Clouds
Lang, A. H., Vora, S., Caesar, H., Zhou, L., Yang, J., & Beijbom, O. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01298 · Cited by 4,673 · cited 1× · see citing works
“Some Pillar-based detectors [2, 23, 48, 49] collapse the height dimension and utilize 2D CNNs for efficient 3D detection.”
MethodMulti-view 3D Object Detection Network for Autonomous Driving
Chen, X., Ma, H., Wan, J., Li, B., & Xia, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.691 · Cited by 3,450 · see citing works
Scalability in Perception for Autonomous Driving: Waymo Open Dataset
Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., Guo, J., Zhou, Y., Chai, Y., Caine, B., et al. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00252 · Cited by 3,437 · cited 2× · see citing works
“Waymo Open Dataset [61] has a wider detection range of 150 m × 150 m compared to the nuScenes dataset.”
BackgroundMethodSECOND: Sparsely Embedded Convolutional Detection
Yan, Y., Mao, Y., & Li, B. (2018) · Sensors · doi:10.3390/s18103337 · Cited by 3,352 · cited 2× · see citing works
“The computation time is mostly taken up by the sparse convolution-based backbone network (VoxelNet [1, 22]), which takes 78ms.”
BackgroundMethodPointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
Shi, S., Wang, X., & Li, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00086 · Cited by 3,093 · cited 2× · see citing works
“There is a rich yet growing literature on BEV-based 3D detection, including multi-modal fusion [4–10], second-stage refinements (surface point pooling [ 3], RoIPool [11– 14], and cross attention modules [4, 15]).”
BackgroundTraining Region-Based Object Detectors with Online Hard Example Mining
Shrivastava, A., Gupta, A., & Girshick, R. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.89 · Cited by 2,686 · cited 1× · see citing works
“The most relevant topic close to our approach is hard example mining [63, 64], which samples hard examples during training.”
BackgroundPV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., & Li, H. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01054 · Cited by 2,341 · see citing works
Center-based 3D Object Detection and Tracking
Yin, T., Zhou, X., & Krähenbühl, P. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01161 · Cited by 2,197 · cited 9× · see citing works
“The neural network makes Positive or Negative predictions given a set of initial object candidates A = { a i , i = 1 , 2 , ... } , which is not limited to anchors [58], point-based anchors [3], and object queries [59].”
BackgroundMethodInfluentialDeformable DETR: Deformable Transformers for End-to-End Object Detection
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020) · arXiv · doi:10.48550/arxiv.2010.04159 · Cited by 1,837 · cited 3× · see citing works
“To enhance the efficiency of object query processing, we employ deformable attention [17] instead of computationally intensive modules such as cross attention [59] or box attention [70].”
Method3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
Graham, B., Engelcke, M., & Maaten, L. V. D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00961 · Cited by 1,788 · see citing works
Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., Yu, Q., & Dai, J. (2022) · arXiv · doi:10.48550/arxiv.2203.17270 · Cited by 1,419 · see citing works
Bevfusion: Multi-task multi-sensor fusion with unified bird’s-eye view representation
Liu, Z., Tang, H., Amini, A., Yang, X., Mao, H., Rus, D. L., & Han, S. (2023) · 2023 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48891.2023.10160968 · Cited by 1,307 · cited 2× · see citing works
“Moreover, our single model FocalFormer3D-F with double-flip testing results performs even better than the BEVFusion [6] with model ensembling.”
MethodLift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
Philion, J., & Fidler, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58568-6_12 · Cited by 1,271 · cited 1× · see citing works
“Unlike heavy lift-splat-shot [32] camera encoders used in BEV-Fusion [5, 6], the multi-view camera images are projected onto a pre-defined voxel space and fused with LiDAR BEV feature.”
MethodPIXOR: Real-time 3D Object Detection from Point Clouds
Yang, B., Luo, W., & Urtasun, R. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00798 · Cited by 1,249 · see citing works
Deep Hough Voting for 3D Object Detection in Point Clouds
Qi, C. R., Litany, O., He, K., & Guibas, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00937 · Cited by 1,244 · cited 1× · see citing works
“…LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or predictions on the sparse representations.”
BackgroundPointPainting: Sequential Fusion for 3D Object Detection
Vora, S., Lang, A. H., Helou, B., & Beijbom, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00466 · Cited by 1,236 · see citing works
3DSSD: Point-Based 3D Single Stage Object Detector
Yang, Z., Sun, Y., Liu, S., & Jia, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01105 · Cited by 1,176 · cited 1× · see citing works
“…LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or predictions on the sparse representations.”
BackgroundSelf-citationDINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L. M., & Shum, H.-Y. (2022) · arXiv · Cited by 1,154 · cited 1× · see citing works
“To address this, we generate noisy queries from ground-truth objects [18, 77, 78], enabling effective training of the model from scratch.”
MethodDN-DETR: Accelerate DETR Training by Introducing Query DeNoising
Li, F., Zhang, H., Liu, S., Guo, J., Ni, L. M., & Zhang, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01325 · Cited by 1,102 · cited 3× · see citing works
“To address this, we generate noisy queries from ground-truth objects [18, 77, 78], enabling effective training of the model from scratch.”
BackgroundMethodVoxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., & Li, H. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16207 · Cited by 1,048 · cited 1× · see citing works
“Modern 3D object detectors, either LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or…”
BackgroundDeep Continuous Fusion for Multi-sensor 3D Object Detection
Liang, M., Yang, B., Wang, S., & Urtasun, R. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01270-0_39 · Cited by 993 · cited 1× · see citing works
“Modern 3D object detectors, either LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or…”
BackgroundTransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers
Bai, X., Hu, Z., Zhu, X., Huang, Q., Chen, Y., Fu, H., & Tai, C.-L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00116 · Cited by 990 · cited 9× · see citing works
“The object candidates obtained from the multi-stage heatmap encoder can be treated as positional object queries [4, 69].”
BackgroundMethodInfluentialSelf-citationSTD: Sparse-to-Dense 3D Object Detector for Point Cloud
Yang, Z., Sun, Y., Liu, S., Shen, X., & Jia, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00204 · Cited by 875 · see citing works
Self-citationMulti-Task Multi-Sensor Fusion for 3D Object Detection
Liang, M., Yang, B., Chen, Y., Hu, R., & Urtasun, R. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00752 · Cited by 723 · see citing works
Self-citationPETR: Position Embedding Transformation for Multi-view 3D Object Detection
Liu, Y., Wang, T., Zhang, X., & Sun, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19812-0_31 · Cited by 666 · see citing works
Gradient Harmonized Single-Stage Detector
Li, B., Liu, Y., & Wang, X. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018577 · Cited by 595 · see citing works
Shi, S., Jiang, L., Deng, J., Wang, Z., Guo, C., Shi, J., Wang, X., & Li, H. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01710-9 · Cited by 571 · see citing works
DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection
Li, Y., Yu, A. W., Meng, T., Caine, B., Ngiam, J., Peng, D., Shen, J., Lu, Y., Zhou, D., Le, Q. V., et al. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01667 · Cited by 563 · cited 1× · see citing works
“Recent multi-modal detectors [5–7, 39, 42, 57] follow the similar paradigm of BEV detectors and incorporate the multi-view image features by physical projection or learnable alignments between LiDAR and cameras.”
Method3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
Weng, X., Wang, J., Held, D., & Kitani, K. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341164 · Cited by 559 · see citing works
Yoo, J. H., Kim, Y., Kim, J., & Choi, J. W. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58583-9_43 · Cited by 520 · see citing works
British Machine Vision Conference 1999
Pridmore, T. (2002) · Image and Vision Computing · doi:10.1016/s0262-8856(02)00002-1 · Cited by 495 · see citing works
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
Chen, Y., Liu, J., Zhang, X., Qi, X., & Jia, J. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02076 · Cited by 490 · cited 1× · see citing works
“Modern 3D object detectors, either LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or…”
BackgroundSelf-citationVoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
Chen, Y., Liu, J., Zhang, X., Qi, X., & Jia, J. (2023) · arXiv · doi:10.48550/arxiv.2303.11301 · Cited by 486 · see citing works
Self-citationPointAugmenting: Cross-Modal Augmentation for 3D Object Detection
Wang, C., Ma, C., Zhu, M. B., & Yang, X. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01162 · Cited by 481 · cited 1× · see citing works
“Recent multi-modal detectors [5–7, 39, 42, 57] follow the similar paradigm of BEV detectors and incorporate the multi-view image features by physical projection or learnable alignments between LiDAR and cameras.”
MethodChen, Y., Liu, S., Shen, X., & Jia, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00987 · Cited by 406 · cited 1× · see citing works
“Modern 3D object detectors, either LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or…”
BackgroundSelf-citationFUTR3D: A Unified Sensor Fusion Framework for 3D Detection
Chen, X., Zhang, T., Wang, Y., Wang, Y., & Zhao, H. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00022 · Cited by 337 · cited 1× · see citing works
“Recent multi-modal detectors [5–7, 39, 42, 57] follow the similar paradigm of BEV detectors and incorporate the multi-view image features by physical projection or learnable alignments between LiDAR and cameras.”
MethodFocal Sparse Convolutional Networks for 3D Object Detection
Chen, Y., Li, Y., Zhang, X., Sun, J. Z., & Jia, J. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00535 · Cited by 332 · see citing works
Self-citationBEVFusion: A Simple and Robust LiDAR-Camera Fusion FrameworkPreprint
Liang, T., Xie, H., Yu, K., Xia, Z., Lin, Z., Wang, Y., Tang, T., Wang, B., & Tang, Z. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.13790 · Cited by 310 · cited 2× · see citing works
“Recent multi-modal detectors [5–7, 39, 42, 57] follow the similar paradigm of BEV detectors and incorporate the multi-view image features by physical projection or learnable alignments between LiDAR and cameras.”
MethodGroup-Free 3D Object Detection via Transformers
Liu, Z., Zhang, Z., Cao, Y., Hu, H., & Tong, X. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00294 · Cited by 303 · cited 1× · see citing works
“There is a rich yet growing literature on BEV-based 3D detection, including multi-modal fusion [4–10], second-stage refinements (surface point pooling [ 3], RoIPool [11– 14], and cross attention modules [4, 15]).”
BackgroundClass-balanced Grouping and Sampling for Point Cloud 3D Object Detection
Zhu, B., Jiang, Z., Zhou, X., Li, Z., & Yu, G. (2019) · arXiv · doi:10.48550/arxiv.1908.09492 · Cited by 297 · see citing works
Embracing Single Stride 3D Object Detector with Sparse Transformer
Fan, L., Pang, Z., Zhang, T., Wang, Y.-X., Zhao, H., Wang, F., Wang, N., & Zhang, Z. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00827 · Cited by 296 · cited 2× · see citing works
“SST [55] applies sparse regional attention and avoids downsampling for small-object detection.”
BackgroundBEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-ViewPreprint
Huang, J., Huang, G., Zhu, Z. D., Ye, Y., & Du, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.11790 · Cited by 292 · see citing works
Prime Sample Attention in Object Detection
Cao, Y., Chen, K., Loy, C. C., & Lin, D. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01160 · Cited by 258 · cited 1× · see citing works
“Recent research [65–67] has further explored soft-sampling, such as adjusting the loss distribution to mitigate foreground-background imbalance issues.”
BackgroundPillarNet: Real-Time and High-Performance Pillar-Based 3D Object Detection
Shi, G., Li, R., & Ma, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20080-9_3 · Cited by 256 · see citing works
LiDAR R-CNN: An Efficient and Universal 3D Object Detector
Li, Z., Wang, F., & Wang, N. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00746 · Cited by 246 · cited 1× · see citing works
“There is a rich yet growing literature on BEV-based 3D detection, including multi-modal fusion [4–10], second-stage refinements (surface point pooling [ 3], RoIPool [11– 14], and cross attention modules [4, 15]).”
BackgroundFusionpainting: Multimodal fusion with adaptive attention for 3d object detection
Xu, S., Zhou, D., Fang, J., Yin, J., Bin, Z., & Zhang, L. (2021) · 2021 IEEE International Intelligent Transportation Systems Conference (ITSC) · doi:10.1109/itsc48978.2021.9564951 · Cited by 237 · see citing works
DSGN: Deep Stereo Geometry Network for 3D Object Detection
Chen, Y., Liu, S., Shen, X., & Jia, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01255 · Cited by 222 · see citing works
Self-citationLearning and example selection for object and pattern detection
Sung, K. K., & Poggio, T. (1996) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 213 · see citing works
Efficient DETR: Improving End-to-End Object Detector with Dense Prior
Yao, Z., Ai, J., Li, B., & Zhang, C. (2021) · arXiv · doi:10.48550/arxiv.2104.01318 · Cited by 190 · cited 2× · see citing works
“Unlike previous methods that used center point features as the query embedding [4, 69], we model the object candidates as box-level queries.”
MethodCenterFormer: Center-Based Transformer for 3D Object Detection
Zhou, Z., Zhao, X., Wang, Y., Wang, P., & Foroosh, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19839-7_29 · Cited by 174 · see citing works
RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
Sun, P., Wang, W., Chai, Y., Elsayed, G. F., Bewley, A., Zhang, X., Sminchisescu, C., & Anguelov, D. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00567 · Cited by 167 · see citing works
SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking
Pang, Z., Li, Z., & Wang, N. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25056-9_43 · Cited by 167 · cited 1× · see citing works
“Interested readers can refer to the original paper [81] for more comprehensive details.”
BackgroundAFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds
Hu, Y., Ding, Z., Ge, R., Shao, W., Huang, L., Li, K., & Liu, Q. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19980 · Cited by 137 · see citing works
Deformable feature aggregation for dynamic multi-modal 3D object detection
Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., & Zhao, F. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20074-8_36 · Cited by 136 · see citing works
Multimodal Virtual Point 3D DetectionPreprint
Yin, T., Zhou, X., & Krähenbühl, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.06881 · Cited by 130 · see citing works
Unifying Voxel-based Representation with Transformer for 3D Object Detection
Li, Y., Chen, Y., Qi, X., Li, Z., Sun, J., & Jia, J. (2022) · arXiv · doi:10.48550/arxiv.2206.00630 · Cited by 125 · cited 1× · see citing works
“Recent multi-modal detectors [5–7, 39, 42, 57] follow the similar paradigm of BEV detectors and incorporate the multi-view image features by physical projection or learnable alignments between LiDAR and cameras.”
MethodSelf-citationVoxel Field Fusion for 3D Object Detection
Li, Y., Qi, X., Chen, Y., Wang, L., Li, Z., Sun, J. Z., & Jia, J. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00119 · Cited by 124 · cited 1× · see citing works
“Modern 3D object detectors, either LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or…”
BackgroundSelf-citationBEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous DrivingPreprint
Zhang, Y., Zhu, Z. D., Zheng, W., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.09743 · Cited by 110 · see citing works
DeepInteraction: 3D Object Detection via Modality Interaction
Yang, Z., Chen, J., Miao, Z., Li, W., Zhu, X., & Zhang, L. (2022) · arXiv · doi:10.48550/arxiv.2208.11112 · Cited by 108 · cited 1× · see citing works
“There is a rich yet growing literature on BEV-based 3D detection, including multi-modal fusion [4–10], second-stage refinements (surface point pooling [ 3], RoIPool [11– 14], and cross attention modules [4, 15]).”
BackgroundDeepInteraction: 3D Object Detection Via Modality Interaction
Yang, Z., Chen, J., Miao, Z., et al. (2022) · neural information processing systems · doi:10.52202/068431-0145 · Cited by 104 · see citing works
AFDet: Anchor Free One Stage 3D Object DetectionPreprint
Ge, R., Ding, Z., Hu, Y., Wang, Y., Chen, S., Huang, L., & Li, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.12671 · Cited by 98 · cited 1× · see citing works
“Some Pillar-based detectors [2, 23, 48, 49] collapse the height dimension and utilize 2D CNNs for efficient 3D detection.”
MethodLearnable Online Graph Representations for 3D Multi-Object Tracking
Zaech, J.-N., Liniger, A., Dai, D., Danelljan, M., & Gool, L. V. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3145952 · Cited by 83 · see citing works
LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception
Ye, D., Zhou, Z., Chen, W., Xie, Y., Wang, Y., Wang, P., & Foroosh, H. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i3.25429 · Cited by 78 · see citing works
Score refinement for confidence-based 3D multi-object tracking
Benbarka, N., Schröder, J., & Zell, A. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636032 · Cited by 72 · see citing works
Fully Sparse 3D Object Detection
Fan, L., Wang, F., Wang, N., & Zhang, Z. (2022) · neural information processing systems · doi:10.52202/068431-0026 · Cited by 65 · see citing works
4D-Net for Learned Multi-Modal Alignment
Piergiovanni, A., Casser, V., Ryoo, M. S., & Angelova, A. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01515 · Cited by 64 · cited 1× · see citing works
“Modern 3D object detectors, either LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or…”
BackgroundDSGN++: Exploiting Visual-Spatial Relation for Stereo-Based 3D Detectors
Chen, Y., Huang, S., Liu, S., Yu, B., & Jia, J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3197236 · Cited by 42 · cited 1× · see citing works
“Modern 3D object detectors, either LiDAR-based [1– 3, 12, 13, 22–29], or Camera-based [30–37], or Multi-Modal [4–8 , 38– 45] 3D object detectors Different from dense detectors, point-based 3D detectors [11, 50–52] directly process point clouds via Point-Net [53, 54] and perform grouping or…”
BackgroundSelf-citationFully Sparse 3D Object DetectionPreprint
Fan, L., Wang, F., Wang, N., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.10035 · Cited by 40 · cited 1× · see citing works
“FSD [56] instead further recognize instances directly on sparse representations obtained by SST [55] and Spar-seConv for long-range detection.”
BackgroundBoxeR: Box-Attention for 2D and 3D Transformers
Nguyen, D.-K., Ju, J., Booij, O., Oswald, M. R., & Snoek, C. G. M. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00473 · Cited by 39 · cited 1× · see citing works
“To enhance the efficiency of object query processing, we employ deformable attention [17] instead of computationally intensive modules such as cross attention [59] or box attention [70].”
MethodKoh, J., Lee, J., Lee, Y., Kim, J., & Choi, J. W. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25200 · Cited by 32 · see citing works
Flagged first, then by citations
8 of the 91 references couldn’t be matched to a known paper.
Research works printed but not linked: 4
- Roddick, Orthographic feature transform for monocular 3d object detection
- 10.1007/978-3-031-20077-9_1 · DOI · Paper page
- 10.1109/tpami.2023.3333838/mm1 · DOI
- Zhou, End-to-end multi-view fusion for 3d object detection in lidar point clouds, 923
Cited by
Sorted by citations
Robustness-Aware 3D Object Detection in Autonomous Driving: A Review and Outlook
Song, Z., Liu, L., Jia, F., Luo, Y., Jia, C., Zhang, G., Yang, L., & Wang, L. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3439557 · Cited by 199 · see citing works
Multimodal fusion and vision–language models: A survey for robot vision
Han, X., Chen, S., Fu, Z., Feng, Z., Fan, L., An, D., Wang, C., Guo, L., Meng, W., Zhang, X., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103652 · Cited by 41 · see citing works
“However, in the real world, the presence of low-quality data seriously affects the performance of multimodal learning, making it difficult for models to work stably in complex environments.”
AlignFusionNet: Efficient Cross-Modal Alignment and Fusion for 3D Semantic Occupancy Prediction
Xu, Z., Qi, L., Du, H.-E., Yang, J., & Chen, Z. (2025) · IEEE Access · doi:10.1109/access.2025.3589858 · Cited by 36 · see citing works
“Although this approach can predict the location and size of the target and generate a compact 3D bounding box [8], it often eliminates detailed features of the detected objects.”
A review of object tracking methods: From general field to autonomous vehicles
Cao, J., Zhang, H., Jin, L., Lv, J., Hou, G., & Zhang, C. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127635 · Cited by 32 · see citing works
SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection
Zhang, H., Liang, L., Zeng, P., Song, X., & Wang, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72761-0_7 · Cited by 35 · see citing works
Xia, Q., Ye, W., Wu, H. X., Zhao, S., Xing, L., Huang, X., Deng, J., Li, X., Wen, C., & Wang, C. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01451 · Cited by 31 · see citing works
Song, Y., & Wang, L. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3518845 · Cited by 28 · see citing works
Image Analysis in Autonomous Vehicles: A Review of the Latest AI Solutions and Their Comparison
Kozłowski, M., Racewicz, S., & Wierzbicki, S. (2024) · Applied Sciences · doi:10.3390/app14188150 · Cited by 22 · see citing works
MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving
Wang, X., Qi, S., Zhao, J., Zhou, H., Zhang, S., Wang, G., Tu, K., Guo, S., Zhao, J., Li, J., et al. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11245874 · Cited by 26 · see citing works
Diffusion Model for Robust Multi-sensor Fusion in 3D Object Detection and BEV Segmentation
Lê, D., Shi, H., Cai, J., & Rezatofighi, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73113-6_14 · Cited by 18 · see citing works
CR3DT: Camera-RADAR Fusion for 3D Detection and Tracking
Baumann, N., Baumgartner, M., Ghignone, E., Kühne, J., Fischer, T., Yang, Y.-H., Pollefeys, M., & Magno, M. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801848 · Cited by 16 · see citing works
“For the detection results, the mAP, NDS, and mAVE scores are reported, while the tracking results use the AMOTA, AMOTP, and IDS metrics.”
InfluentialSparse agent transformer for unified voxel and image feature extraction and fusion
Zhang, H., Wan, J., He, Z., Song, J., Yang, Y. F., & Yuan, D. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102455 · Cited by 14 · see citing works
SwiftPillars: High-Efficiency Pillar Encoder for Lidar-Based 3D Detection
Jin, X., Liu, K., Ma, C., Yang, R., Hui, F., & Wu, W. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i3.28040 · Cited by 14 · see citing works
SEED: A Simple and Effective 3D DETR in Point Clouds
Liu, Z., Hou, J., Ye, X., Wang, T., Wang, J., & Bai, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73247-8_7 · Cited by 14 · see citing works
CatmullRom Splines-Based Regression for Image Forgery Localization
Zhang, L., Xu, M., Li, D., Du, J., & Wang, R. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i7.28548 · Cited by 13 · see citing works
A review of 3D object detection based on autonomous driving
Wang, H., Chen, X., Yuan, Q., & Liu, P. (2024) · The Visual Computer · doi:10.1007/s00371-024-03480-6 · Cited by 16 · see citing works
“Chen et al. [112] proposed FocalFormer3D to solve the False Neg-atives problem.”
Zheng, T., Zhang, Y., & Ma, T. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13417 · Cited by 12 · see citing works
Zou, J., Huang, T., Yang, G., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72670-5_17 · Cited by 10 · see citing works
Mushtaq, H., Deng, X., Alizadehsani, R., et al. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.126359 · Cited by 10 · see citing works
Han, L., Wang, J., Li, C., Tao, F., & Fu, Z. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3550506 · Cited by 10 · see citing works
Boroujeni, S. P. H., Mehrabi, N., Alzorgan, H., Fazeli, M., & Razi, A. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.105944 · Cited by 9 · see citing works
MSPE-Fusion: A multimodal 3D object detection method with multi-sensor perception enhanced fusion
Yu, S., Wang, X., Ci, Y., Li, Y., Zhou, M., Dong, X., & Cai, M. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130486 · Cited by 7 · see citing works
Multi-Modal BEV Enhancement Fusion for 3D Object Detection in Autonomous Driving
Chen, M., Yang, M., Zhang, Y., Han, T., Li, X., Zhao, H., & Liu, P. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3589581 · Cited by 7 · see citing works
Zhu, Y., Jia, X., Yang, X., & Yan, J. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128084 · Cited by 7 · see citing works
LSPConv: local spatial projection convolution for point cloud analysis
Zhang, H., Wang, K., Zhong, C., Yun, K., Wang, Z., Yang, Y., & Tao, X. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.1738 · Cited by 7 · see citing works
LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception
Zhou, Z., Ye, D., Chen, W., Xie, Y., Wang, Y., Wang, P., & Foroosh, H. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610374 · Cited by 7 · see citing works
MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation
Zhao, X. F., Zhang, X., Yang, D., Sun, M., Li, M., Wang, S., & Zhang, L. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681360 · Cited by 7 · see citing works
A Point-Based Approach to Efficient LiDAR Multi-Task Perception
Lang, C., Braun, A., Schillingmann, L., et al. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802240 · Cited by 7 · see citing works
“This dataset suffers from class imbalance, which makes the detection task more challenging. b) SemanticKITTI: The SemanticKITTI [31] dataset contains 23k training samples and 20k testing samples in autonomous driving scenes with panoptic segmentation annotations for 8 thing and 12 stuff classes.”
MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models
Meier, J., Inchingolo, L., Dhaouadi, O., Xia, Y., Kaiser, J., & Cremers, D. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127874 · Cited by 6 · see citing works
“Although LiDAR-based detectors [2], [3], [4], [5] provide high precision due to the accurate depth measurement, they are costly and require complex infrastructure.”
CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection With IoU Joint Prediction
Ning, Z., Liu, Z., Gao, X., Zuo, Y., Yang, J., Fang, Y., & Liu, W. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3600527 · Cited by 5 · see citing works
3D Object Detection Using Multiple-Frame Proposal Features Fusion
Minyuan, H., Leung, H., & Hou, M. (2023) · Sensors · doi:10.3390/s23229162 · Cited by 5 · see citing works
“[32] focuses on false negative examples by using heatmap prediction to excavate hard samples and omitting the training of easy positive candidates.”
BackgroundGATR: Transformer Based on Guided Aggregation Decoder for 3D Multi-Modal Detection
Luo, Y., He, L., Ma, S., et al. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3422812 · Cited by 5 · see citing works
Oladele, D. A., Markus, E. D., & Abu-Mahfouz, A. M. I. (2025) · AI · doi:10.3390/ai6040082 · Cited by 6 · see citing works
CMD: A Cross Mechanism Domain Adaptation Dataset for 3D Object Detection
Deng, J., Ye, W., Wu, H. Y., Huang, X., Xia, Q., Li, X. S., Fang, J., Li, W., Wen, C., & Wang, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72998-0_13 · Cited by 5 · see citing works
Clustering and Anomaly Detection in Embedding Spaces for the Validation of Automotive Sensors
Fertig, A., Balasubramanian, L., & Botsch, M. (2024) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv55156.2024.10588817 · Cited by 4 · see citing works
“In this work, for the camera recordings, the object tracking method StreamPETR [29] was chosen, while the method FocalFormer3D [30] was used for the lidar recordings.”
MethodClass Prototypical Loss for Enhanced Feature Separation in 3D Object Detection
Perez, M., Agudo, A., Dubbelman, G., & Jancura, P. (2024) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc58415.2024.10919676 · Cited by 4 · see citing works
“Recent 3D object detectors [1]–[5] use a neural network to extract a Birds-Eye-View (BEV) feature map [6] and then apply a detection head on top of that representation to determine the location, orientation, and object class.”
Teleoperating Autonomous Vehicles Over Commercial 5G Networks: Are We There Yet?
Fezeu, R. A. K., Carpenter, J., Zende, R., Divakarla, S. G. L., Varyani, N., Bilal, F., Sleder, S., Naik, N., Joly, D., Ramadan, E., et al. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3686751 · Cited by 5 · see citing works
“However, the distribution has a long tail, with 72.3% of the frames with delay between 50 and 100 ms, 16.2% with delay between 100 ms and 500 ms, and 8.7% with a network delay larger than 500 ms. Perceptual Quality Deviation .”
InfluentialHua, C., Zheng, X., Kuang, X., Zhang, W., Jiang, C., Chen, Z., & Yu, B. (2025) · Sensors · doi:10.3390/s25051581 · Cited by 4 · see citing works
“Similarly, channel attention emphasizes the importance of features from specific channels, ensuring that the network focuses on the most important attributes, such as object boundaries and fine-grained details [29].”
Mushtaq, H., Latif, S., Ilyas, M., Mohsin, S. M., & Ali, M. (2025) · IEEE Access · doi:10.1109/access.2025.3558780 · Cited by 5 · see citing works
KPV3D: Enhancing Multiview 3-D Vehicle Detection With 2-D Keypoint Priors
Yao, Z., Xiong, Z., Liu, X., & Wu, X. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3443353 · Cited by 5 · see citing works
“Chen et al. [40] employ a multistage query generation process to uncover hard-to-detect objects and utilize a box-level transformer decoder to differentiate potential candidates.”
BackgroundV-Fusion: 2D Detection-enhanced Multimodal 3D BEV Object Detection
Li, Z., Zhao, X. Y., Jingwei, B., Liu, B., Li, W., & Zhang, L. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889489 · Cited by 4 · see citing works
DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction
Yang, Z., Dong, Y., Wang, J., et al. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3610634 · Cited by 4 · see citing works
“By combining these complementary data sources, the accuracy and robustness of occupancy predic-*”
Robust 3D Object Detection in Complex Traffic via Unified Feature Alignment in Bird’s Eye View
Liu, A., Zhang, Y., Shi, H., & Chen, J. (2025) · World Electric Vehicle Journal · doi:10.3390/wevj16100567 · Cited by 3 · see citing works
A New Architecture for Neural Enhanced Multiobject Tracking
Wei, S., Liang, M., & Meyer, F. (2024) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion59988.2024.10706394 · Cited by 3 · see citing works
“Together with the probability of existence, the detection score is used to compute the final AMOTA score for each PO (see [26] for details).”
BackgroundMethodInfluentialDeepMonitor: A comprehensive approach for real‐time hazard detection for industrial safety
Lee, S., Baek, Y., Oh, H., & Kim, S. H. (2025) · ETRI Journal · doi:10.4218/etrij.2024-0284 · Cited by 3 · see citing works
UniSense: Spatial-Uncertainty-Aware Collaborative Sensing for Autonomous Driving
Ren, H., Zhang, W., Shi, S., Zhang, X. Y., Zhang, L., & Zhang, Y. (2025) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3711875.3729130 · Cited by 3 · see citing works
3D Visual Grounding-Audio: 3D scene object detection based on audio
Zhang, C., Cai, Z., Chen, X., Da, F., & Gai, S. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128637 · Cited by 3 · see citing works
BEVFusion With Dual Hard Instance Probing for Multimodal 3D Object Detection
Kim, T., & Kim, J. (2025) · IEEE Access · doi:10.1109/access.2025.3538866 · Cited by 3 · see citing works
“To address the issue of FN, FocalFormer3D [43] introduces Hard Instance Probing (HIP), a multi-stage strategy designed to progressively enhance the detection of challenging objects.”
InfluentialLiu, M., Wu, M., Wang, W., Liu, P., Chang, K., Li, M., & Piao, C. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3564413 · Cited by 3 · see citing works
Temporal-Enhanced Radar and Camera Fusion for Object Detection
Kong, L., Wang, Y., Chang, D., & Zhao, Y. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3700442 · Cited by 2 · see citing works
JDT3D: Addressing the Gaps in LiDAR-Based Tracking-by-Attention
Cheong, B., Zhou, J., & Waslander, S. L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72848-8_10 · Cited by 2 · see citing works
Multimodal feature adaptive fusion for anchor-free 3D object detection
Wu, Y., Wang, J., Li, H., Ai, X., & Li, X. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06454-w · Cited by 2 · see citing works
Toward Unified 3D Object Detection via Algorithm and Data Unification
Li, Z., Xu, X., Lim, S.-N., & Zhao, H. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3574363 · Cited by 2 · see citing works
“To handle this problem, there are works that exclusively use depth sensors, which yield precise 3D bounding boxes but may struggle with accurate category prediction due to the lack of semantic information in point clouds [25], [26].”
BackgroundMultimodal and view image processing for three-dimensional object detection in autonomous driving
Wang, Y., Dong, H., & Hua, B. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112921 · Cited by 2 · see citing works
Hariya, K., Inoshita, H., Fukuda, Y., YONEDA, K., & Suganuma, N. (2025) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-025-00598-2 · Cited by 2 · see citing works
PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Tasks
Wang, X., Lin, Z., Xia, Z., & Wang, Y. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00423 · Cited by 2 · see citing works
3-D Object Detection for Railway: A Comprehensive Survey
Lian, L., Qin, Y., Cao, Z., Gao, Y., Liu, Z., Li, Q., & Cheng, X. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3684649 · Cited by 2 · see citing works
“…developed to optimize trans-former interactions [161], [162], [163], [164], [165], [166], [167], implement sparse or object-level fusion [168], [169], [170], and introduce novel operators like MambaFusion [171] or specialized point-voxel convolutions [172], [173], [174], [175], [176], [177], [178].”
GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-Based Transformer
Jin, X., Su, H., Ma, C., Liu, K., Wu, W., Hui, F., & Yan, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02495 · Cited by 2 · see citing works
Co-Fix3D: Enhancing 3D Object Detection With Collaborative Refinement
Li, W., Zou, Q., Chen, C., et al. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3555859 · Cited by 2 · see citing works
“To overcome this, FocalFormer3D [6] (Fig.”
InfluentialLUOT: LiDAR–UWB Object Tracking With Zero ID Switches and Centimeter-Level Precision
Li, Y., Zou, Y., Zhang, X., Lu, X., Fan, J., Zang, Z., & Zhang, D. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3608808 · Cited by 2 · see citing works
“NVIDIA implemented its own FocalFormer3D 14 [9] detector within SimpleTrack, achieving SOTA.”
TA-TOS: Terrain-Aware Tiny Obstacle Segmentation Based on MRF Road Modeling Using 3-D LiDAR Scans
Ming, N., Qian, Y., Feng, C., Wang, C., & Yang, M. Z. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3574769 · Cited by 1 · see citing works
“Chen et al. proposed FocalFormer3D [37], which introduced a hierarchical query generation strategy and a novel box-level transformer decoder for difficult object discovery and detection.”
A method for noise-suppressed multimodal feature integration in urban scene detection
Han, X.-J., Qu, Z., & Xia, S. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104290 · Cited by 1 · see citing works
FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object Detection
Dang, C., Duan, Z., An, P., Zhang, X., Hu, X., & Ma, J. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01587 · Cited by 1 · see citing works
Coupling and Decoupling: Towards Temporal Feedback for 3D Object Detection
Cui, Y., Zou, Z., Ye, X., Tan, X., Li, Z., & Fang, Z. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3599031 · Cited by 1 · see citing works
LRTG3D: Large receptive field 3D object detection with truncated Gaussian denoising query
Li, C., Mao, X., Ning, Z., Yang, J., & Liu, W. (2025) · Pattern Recognition Letters · doi:10.1016/j.patrec.2025.08.024 · Cited by 1 · see citing works
Inferring Driving Maps by Deep Learning-Based Trail Map Extraction
Hubbertz, M., Colling, P., Han, Q., et al. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00228 · Cited by 1 · see citing works
Multi-Layer Self-Assessment with Filtering for 3D Object Detection in Autonomous Vehicles
Yatbaz, H. Y., Koufos, K., Dianati, M., et al. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3776551 · Cited by 1 · see citing works
DCI-PRNet: 3D Object Detection Network via Dual Cross-modal Interaction and Progressive Reasoning
Chan, S., Duan, B., Fan, X., et al. (2025) · doi:10.1109/ijcnn64981.2025.11229135 · Cited by 1 · see citing works
PLPFusion: Plane-Line-Pixel Fully Sparse Fusion for Robust Multi-Modal 3D Object Detection
Hou, J., Song, H., Li, J. W., Lin, Y., Huang, T., He, J., He, X., & Yang, J. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3644414 · Cited by 2 · see citing works
DepthFusion: Depth-Aware Hybrid Feature Fusion for LiDAR-Camera 3D Object Detection
Ji, M., Yang, J. J., & Zhang, S. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668596 · Cited by 1 · see citing works
A Bayesian Multiobject Tracking Approach with Neural-Enhanced Motion and Measurement Models
Wei, S., Liang, M., & Meyer, F. (2025) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/ieeeconf67917.2025.11443878 · Cited by 1 · see citing works
SFMNet: Sparse Focal Modulation for 3D Object Detection
Shrout, O., & Tal, A. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00608 · Cited by 1 · see citing works
“To mitigate this, VoTr [31] implements local and dilated attention, focusing on sparse voxel interactions.”
Cheong, B., Wang, L., Papais, S., & Waslander, S. L. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00325 · Cited by 1 · see citing works
Online Monitoring Framework for Automotive Time Series Data using JEPA Embeddings
Fertig, A., Sekaran, K. C., Balasubramanian, L., et al. (2026) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv66570.2026.11624095 · Cited by 1 · see citing works
“The error on the feature f is denoted as ϑ f ∈ R and drawn for each object from a feature-specific normal distribution N ( µ f , σ 2 f ) . to For instance, if a sampled error ϑ v is applied the velocity feature v at the specific timestep t ∈ + , this is formulated as: v [ t ] + ϑ v .”
NIV-SSD: Neighbor IoU-voting single-stage object detector from point cloud
Liu, S., Wang, D., Wang, Q., & Huang, K. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127987 · Cited by 1 · see citing works
Camera-Radar-Based Adaptive Cross Attention Fusion for Multimodal Object Detection
Jhong, S.-Y., Chang, W., Hsu, H.-C., et al. (2024) · International Automatic Control Conference · doi:10.1109/cacs63404.2024.10773133 · Cited by 1 · see citing works
Self-citationRet3D: rethinking object relations for efficient 3D object detection
Wu, Y., ZHANG, D., Liu, Y., ZHANG, L., & Cheng, M. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2024-0295 · Cited by 1 · see citing works
Valeo4Cast: A Modular Approach to End-to-End Forecasting
Xu, Y., Zablocki, É., Boulch, A., Puy, G., Chen, M., Bartoccioni, F., Samet, N., Siméoni, O., Gidaris, S., Vu, T.-H., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91767-7_1 · Cited by 1 · see citing works
IRBEVF-Q: Optimization of Image–Radar Fusion Algorithm Based on Bird’s Eye View Features
Cai, G., Chen, F., & Guo, E. (2024) · Sensors · doi:10.3390/s24144602
Focusing 3D Small Objects with Object Matching Set Abstraction
Guo, L., Song, N., Hu, J., et al. (2025) · Applied Sciences · doi:10.3390/app15084121
Data Fusion-Based Joint 3D Object Detection Using Point Clouds and Images
Lyu, J., Wang, S., Qi, Y., et al. (2025) · Electronics · doi:10.3390/electronics14122414
Cai, C., Yan, H., Huang, Y., et al. (2025) · doi:10.1109/aaicv66571.2025.00007
Towards generalizable and interpretable three-dimensional tracking with inverse neural rendering
Ost, J., Banerjee, T., Bijelic, M., et al. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01083-x
Explore the LiDAR-Camera Dynamic Adjustment Fusion for 3D Object Detection
Yang, Y., Gao, X., Wang, T., Hao, X., Shi, Y., Tan, X., & Ye, X. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128091
ImVoxelENet: Image to Voxels Epipolar Transformer for Multi-View RGB-Based 3D Object Detection
Xu, G., Liu, H., Leng, B., et al. (2025) · Computational Visual Media · doi:10.26599/cvm.2025.9450504
MGAF: LiDAR-Camera 3D Object Detection With Multiple Guidance and Adaptive Fusion
Fan, B., Li, X., Zhou, Y., Xia, C., Fan, H., Xu, F., & Tian, J. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3612958
Simpler Is Better: Revisiting Doppler Velocity for Enhanced Moving Object Tracking with FMCW LiDAR
Zeng, Y., Wu, T., Qi, S., Li, J., Duan, X., & Yu, Y. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246618
“To obtain accurate spatial information on objects, state-of-the-art 3D Multi-Object Tracking (MOT) methods primarily rely on the three-dimensional point clouds provided by TOF LiDAR as input [6], [7], [8].”
Bayesian Multiobject Tracking With Neural-Enhanced Motion and Measurement Models
Wei, S., Liang, M., & Meyer, F. (2026) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2026.3654026
“The ROI is identified on the BEV feature map [60], [61], [62] in R 180 × 180 × 128 corresponding to raw measurement from time k − 1 .”
InfluentialBidirectional Supervised Fusion for Cross-Modal 3D Object Detection in Autonomous DrivingPreprint
Yue, S., Liu, J., Hao, W., Zhou, S., & cai, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6205840
RG-Attn: Radian Glue Attention for Multi-Modal Multi-Agent Cooperative Perception
Li, L., Yang, K., Zhang, W., Wang, X., & Sun, C. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00187
“Transformer structures, such as ViT and Point-Transformer [14], [15], have further elevated the performance of both single-modality tracks, ushering in a new era.”
ID-SSLNet: Intensity Difference-Based Semi-Solid-State LiDAR Planar Markers Detection Network
Chen, Z., Zhang, Z., Pan, S., Tao, X., & Gao, W. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3665301
“However, due to the availability and widespread adoption of mainstream datasets [2], [3], [4], most current LiDAR-based object detection studies primarily focus on mechanical LiDAR characteristics [5], [6], [7].”
StreamCMT: Prior-Guided Multimodal Temporal Fusion for Sparse 3D Object Detection
Huang, Y., & Yuansheng, L. I. U. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3671538
MVOD - A Multi-View Fusion Network for 3D Obstacle Detection with Point Clouds and Images
Wang, J., Wang, Z., Mi, H., et al. (2025) · International Conference on Robotics, Automation and Artificial Intelligence (RAAI) · doi:10.1109/raai67517.2025.11423379
Surface3D: A Surface-Aware Framework for Refining 3D Object Detection
Liu, M., Hou, Y., Yurtsever, E., Zhou, X., Zhang, J., Zhang, H., & Knoll, A. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423169
“Nevertheless, current state-of-the-art 3D detection architectures [6], [8]– [10] often overlook surface-level information or focus on reconstructing entire vehicle structures [11], [12], resulting in inefficient and computationally expensive methods.”
Target-aware proposal-level fusion for multi-modal three-dimensional detection
Zhao, Z., Wu, B., Yin, Y., Zhang, J., Li, Y., Zeng, Y., & Gao, H. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114576
AMTFusion: Boosting 3D Object Detection by Adaptive Multi-Modal Temporal Fusion and Augmentation
Tian, W., Du, Z., Zhao, X., & Yu, Q. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3679483
Occlusion Aware Graph Transforemr for 3D Multi-Object Tracking
Wei, J., Gao, H., Nie, J., Cai, Z., & Liu, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463703
He, Y., Zhao, L., Deng, T., Fang, Z., & Chen, W. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3687354 · Cited by 1 · see citing works
Beyond Sparsity: Receptive Field Expansion and Cross-Task Fusion for LiDAR Multi-Task Perception
Huang, S., Zhang, R., Liu, S., Bian, Y., & Qin, X. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3688337
“InFocalFormer3D[25],theattentionmechanismdiscoversthese hard-to-detectobjectsthroughmulti-stagequerygenerationand effectivelydistinguishesnumerouscandidateproposalsviaa box-leveltransformerdecoder.”
Wang, S., Zheng, X., Zhang, Y. J., Ran, S., Lan, R., & Zhu, H. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11487542
- Authors
- Chen, Y., Yu, Z., Chen, Y., Lan, S., Anandkumar, A., Jia, J., & Alvarez, J. M.
- Affiliations
- Chinese University of Hong Kong (HK)
- Nvidia (United Kingdom) (GB)
- Caltech
- NVIDIA
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 8360-8371
- OpenAlex
- W4390872444
- Semantic Scholar
- ef80a308b548f582ac52419dffaa48f53db8a4f8
- Cited by
- 119
- References
- 91
- Citations by year
- 2026: 35 · 2025: 53 · 2024: 30 · 2023: 1
- FWCI
- 12.73
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-nd)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
- Keywords
- 3D object detection, false negative reduction, LiDAR, autonomous driving, object tracking, multimodal detection, nuScenes, Waymo
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
