The DOI matches its Crossref record; 66 of the 82 references it cites were found in a registry or an index.
Categorical Depth Distribution Network for Monocular 3D Object Detection
Open accessAbstract
Monocular 3D object detection is a key problem for autonomous vehicles, as it provides a solution with simple configuration compared to typical multi-sensor systems. The main challenge in monocular 3D detection lies in accurately predicting object depth, which must be inferred from object and scene cues due to the lack of direct range measurement. Many methods attempt to directly estimate depth to assist in 3D detection, but show limited performance as a result of depth inaccuracy. Our proposed solution, Categorical Depth Distribution Network (CaDDN), uses a predicted categorical depth distribution for each pixel to project rich contextual feature information to the appropriate depth interval in 3D space. We then use the computationally efficient bird’s-eye-view projection and single-stage detector to produce the final output detections. We design CaDDN as a fully differentiable end-to-end approach for joint depth estimation and object detection. We validate our approach on the KITTI 3D object detection benchmark, where we rank 1stamong published monocular methods. We also provide the first monocular 3D detection results on the newly released Waymo Open Dataset. We provide a code release for CaDDN which is made available.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“A popular BEV framework that generates BEV features is based on depth information [46, 32, 34], but this paradigm is sensitive to the accuracy of depth values or the depth distributions.”
From BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers (2022) · cites this paper as [34]
In the citing paper
“BEV-based approaches have not shown significant advantages over other paradigm in 3D object detections [47, 31, 34].”
From BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers (2022) · cites this paper as [34]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Microsoft 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
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Focal 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
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Are 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
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2858826 · Cited by 9,556
Research works printed but not linked: 4
- mani, 2020, Monolayout: Amodal scene layout from a single image, WACV
- ma, 2020, Rethinking pseudolidar representation, ECC
- shi, 2020, Distance-normalized unified representation for monocular 3d object detection, ECC
- roddick, 2018, Orthographic feature transform for monocular 3D object detection, BMV
Cited by
Sorted by citations
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
BEVDepth: Acquisition of Reliable Depth for Multi-View 3D Object Detection
Li, Y., Ge, Z., Yu, G., Yang, J., Wang, Z., Shi, Y., Sun, J., & Li, Z. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i2.25233 · Cited by 939
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
Wang, T., Zhu, X., Pang, J., & Lin, D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00107 · Cited by 683
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
Wang, T., Zhu, X., Pang, J., & Lin, D. (2021) · arXiv · doi:10.48550/arxiv.2104.10956 · Cited by 683
PETR: 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 764
DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
Yu, H., Luo, Y., Shu, M., Huo, Y., Yang, Z., Shi, Y., Guo, Z., Li, H., Hu, X., Yuan, J., et al. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.02067 · Cited by 577
“The success of deep neural networks brings the promise of solving AD’s core requirement to perceive the surrounding environment from point cloud [15,20,28], images [7, 18] or multi-modality data [21, 24].”
BackgroundShi, 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 602
“LSS (Philion and Fidler, 2020) andCaDDN (Reading et al., 2021) predicts depth distribution to “lift” the 2D image features to a BEV feature map for 3D detection.”
Background3D Object Detection for Autonomous Driving: A Comprehensive Survey
Mao, J., Shi, S., Wang, X., & Li, H. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01790-1 · Cited by 529
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction
Huang, Y., Zheng, W., Zhang, Y., Zhou, J., & Lu, 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/cvpr52729.2023.00890 · Cited by 379
“Recent studies in BEV-based perception focus on how to effectively transform features from the image space to the BEV space [20, 26, 27, 35, 36, 48].”
BackgroundBEVFormer: Learning Bird’s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers
Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lü, T., Qiao, Y., & Dai, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3515454 · Cited by 357
ST-P3: End-to-End Vision-Based Autonomous Driving via Spatial-Temporal Feature Learning
Hu, S., Chen, L., Wu, P., Li, H., Yan, J., & Tao, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19839-7_31 · Cited by 273
Multi-Modal 3D Object Detection in Autonomous Driving: A Survey and Taxonomy
Wang, L., Zhang, X., Song, Z., Bi, J., Zhang, G., Wei, H., Tang, L., Yang, L., Li, J., Jia, C., et al. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3264658 · Cited by 291
“On the contrary, image-based methods [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50] provides sufficient texture and context information but insufficiently geometrical information.”
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
Lu, Y., Ma, X., Yang, L., Zhang, T., Liu, Y., Chu, Q., Yan, J., & Ouyang, W. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00310 · Cited by 265
“For instance, compared with the recently proposed CaDNN [38] utilizing LiDAR signals as supervision of depth estimation sub-task, our method still obtains 0.”
MethodInfluentialSurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving
Wei, Y., Zhao, L., Zheng, W., Zhu, Z. H., Zhou, J., & Lu, J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01986 · Cited by 327
“Depth-based methods explicitly predict depth maps for image inputs to extract 3D geometric information of the scene before perception [54, 36, 44, 39, 28, 35, 30, 42, 21, 65].”
MethodV2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception
Xu, R., Xia, X., Li, J., Li, H., Zhang, S., Tu, Z., Meng, Z., Xiang, H., Dong, X., Song, R., et al. (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/cvpr52729.2023.01318 · Cited by 282
“(1) Camerabased detection denotes approaches that detect 3D objects from a single or multiple RGB images [16, 32, 33, 35, 42].”
BackgroundMonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
Huang, K., Wu, T.-H., Su, H.-T., & Hsu, W. H. (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/cvpr52688.2022.00398 · Cited by 238
BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation
Li, Z., Wang, X., Liu, X., & Jiang, J. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3416065 · Cited by 301
“A widespread of various depth-depended tasks related to autonomous driving [2], [3], [4], [5], [6], virtual reality [7], [8], and scene understanding [9], [10], [11], [12] provide strong demand for effective MDE methods that can accurately reconstruct the 3D world.”
BackgroundMonoDETR: Depth-guided Transformer for Monocular 3D Object Detection
Zhang, R., Qiu, H., Wang, T., Guo, Z., Cui, Z., Qiao, Y., Li, H., & Gao, P. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00840 · Cited by 250
OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction
Zhang, Y., Zhu, Z. D., & Du, D. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00865 · Cited by 282
“Considering the dimension gap between the 2D image input and the 3D prediction, recent studies for vision-based 3D perception first construct the BEV feature representations and then perform various downstream tasks on the BEV space [19, 28, 30, 37, 58, 38, 60, 40, 18, 1, 42].”
BackgroundMethodPolarFormer: Multi-Camera 3D Object Detection with Polar Transformer
Jiang, Y., Zhang, L., Miao, Z., Zhu, X., Gao, J., Hu, W., & Jiang, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25185 · Cited by 200
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 219
LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross- Modal Fusion
Li, X. S., Ma, T., Hou, Y., Shi, B., Yang, Y., Liu, Y., Wu, X., Chen, Q., Li, Y., Qiao, Y., et al. (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/cvpr52729.2023.01681 · Cited by 199
“For image-based 3D object detection, since depth information is not directly accessible from images, some works [39, 44, 55, 69] first conduct depth estimation to generate pseudo-LiDAR representations or lift 2D features into the 3D space, then perform object detection in the 3D space.”
MethodDelving Into the Devils of Bird’s-Eye-View Perception: A Review, Evaluation and Recipe
Li, H., Sima, C., Dai, J., Wang, W., Lu, L., Wang, H., Zeng, J., Li, Z., Yang, J., Deng, H., et al. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3333838 · Cited by 211
“The main difference between LSS [56] and CaDDN [45] is that CaDDN uses depth ground truth to supervise its categorical depth distribution prediction, thus owing a superior depth network to extract 3D information from 2D space.”
BackgroundMethodInfluentialLearning for Vehicle-to-Vehicle Cooperative Perception Under Lossy Communication
Li, J., Xu, R., Liu, X., Ma, J., Chi, Z., Ma, J., & Yu, H. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3260040 · Cited by 161
“Based on recently available sensor modality, 3D detection method can be roughly divided into three categories: (1) Camera-based detection methods where approaches detect 3D objects using a single or multiple RGB images [18]–[20].”
Multi-Sensor Fusion Technology for 3D Object Detection in Autonomous Driving: A Review
Wang, X., Li, K., & Chehri, A. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3317372 · Cited by 179
“In recent years, most camera-based 3D object detection has been done using monocular cameras [13], [14], [15], [16], [17], [18], [19]. b) Multi-vision camera-based: Currently, self-driving vehicles are typically outfitted with numerous cameras to capture forward or 360 information from multiple…”
BackgroundSimple-BEV: What Really Matters for Multi-Sensor BEV Perception?
Harley, A. W., Fang, Z., Li, J., Ambruş, R., & Fragkiadaki, K. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160831 · Cited by 184
“Depth-based unprojection: Several works estimate perpixel depth with a monocular depth estimator, either pretrained for depth estimation [9, 20, 21] or trained simply for the end-task [10, 22, 23], and used the depth to place features at their estimated 3D locations.”
EPNet++: Cascade Bi-Directional Fusion for Multi-Modal 3D Object Detection
Liu, Z., Huang, T., Li, B., Chen, X., Wang, X., & Bai, X. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3228806 · Cited by 168
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
Liu, X., Xue, N., & Wu, T. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20074 · Cited by 165
Vision-Centric BEV Perception: A Survey
Ma, Y., Wang, T., Bai, X., Yang, H., Hou, Y., Wang, Y., Qiao, Y., Yang, R., & Zhu, X. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3449912 · Cited by 218
“In addition to classical auxiliary tasks like depth estimation [41], [46], monocular 2D and 3D detection [57], [142], and 2D lane detection [88], several works also devise schemes for knowledge distillation from cross-modality settings such as monocular learn from stereo [146] and stereo learn from LiDAR [147].”
BackgroundMethodInfluentialCRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception
Kim, Y., Shin, J., Kim, S., Lee, I.-J., Choi, J. W., & Kum, D. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01615 · Cited by 155
“This section provides the experimental settings for the main results and ablation studies.”
BackgroundMethodZhou, T., Chen, J., Shi, Y., Jiang, K., Yang, M., & Yang, D. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3240287 · Cited by 161
“The last and the most concerned ones project image-view features to BEV through a view transformer, such as Imvoxelnet [28], BEVDet [15], and CaDNN [29].”
BackgroundRCFusion: Fusing 4-D Radar and Camera With Bird’s-Eye View Features for 3-D Object Detection
Zheng, L., Li, S., Tan, B., Yang, L., Chen, S., Huang, L., Bai, J., Zhu, X., & Ma, Z. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3280525 · Cited by 165
3D Object Detection From Images for Autonomous Driving: A Survey
Ma, X., Ouyang, W., Simonelli, A., & Ricci, E. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3346386 · Cited by 164
“Moreover, existing feature lifting-based methods [23], [83], [84], [85], [86] further collapse the 3D voxel features along the vertical dimension, corresponding to the height of objects, to generate the BEV features before estimating final results.”
BackgroundMethodInfluential3D Object Detection from Images for Autonomous Driving: A Survey
Ma, X., Ouyang, W., Simonelli, A., & Ricci, E. (2022) · arXiv · doi:10.48550/arxiv.2202.02980 · Cited by 147
“Moreover, existing feature lifting-based methods [23], [83], [84], [85], [86] further collapse the 3D voxel features along the vertical dimension, corresponding to the height of objects, to generate the BEV features before estimating final results.”
BackgroundMethodInfluentialSparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos
Liu, H., Teng, Y., Lu, T., Wang, H., & Wang, L. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01703 · Cited by 154
“Several works [53, 43, 51, 39] incorporates depth information to deal with this problem.”
BackgroundAutoShape: Real-Time Shape-Aware Monocular 3D Object Detection
Liu, Z., Zhou, D., Lu, F., Fang, J., & Zhang, L. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01535 · Cited by 151
“In addition, most of the existing methods such as [27, 26, 37, 5, 34], need to estimate the depth map, resulting in a heavy computation burden in inference.”
MethodFB-BEV: BEV Representation from Forward-Backward View Transformations
Li, Z., Yu, Z., Wang, W., Anandkumar, A., Lü, T., & Álvarez, J. M. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00637 · Cited by 151
“CaDDN [17] and BEVDepth [15] proposes the use of LiDAR point clouds to generate depth ground truth for supervising the depth prediction module.”
MethodDeep Learning-Based Image 3-D Object Detection for Autonomous Driving: Review
Alaba, S. Y., & Ball, J. E. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3235830 · Cited by 140
“[72] proposed a categorical depth distribution network (CDDN) for monocular 3-D object detection.”
BackgroundBEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection
Yang, L., Yu, K., Tang, T., Li, J., Yuan, K., Wang, L., Zhang, X., & Chen, P. (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/cvpr52729.2023.02070 · Cited by 127
“Following LSS [24], depth-based methods [9, 10, 25] explicitly predict the depth distribution and use it to construct the 3D volumetric feature.”
MethodLXL: LiDAR Excluded Lean 3D Object Detection With 4D Imaging Radar and Camera Fusion
Xiong, W., Liu, J., Huang, T., Han, Q., Xia, Y., & Zhu, B. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3321240 · Cited by 141
“The third type involves lifting pixels into a point cloud or voxels [15], [16], [17], [21], [27] and applying networks designed for LiDAR-based 3D object detection.”
BackgroundMethodInfluentialCRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer
Kim, Y., Kim, S., Choi, J. W., & Kum, D. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25198 · Cited by 130
Fast-CLOCs: Fast Camera-LiDAR Object Candidates Fusion for 3D Object Detection
Pang, S., Morris, D., & Radha, H. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00380 · Cited by 125
Voxel 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 128
“The image-to-voxel dense rendering is usually resourceintensive or requires extra models for depth prediction [25, 47].”
BackgroundThink Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving
Jia, X., Wu, P., Chen, L., Xie, J., He, C., Yan, J., & Li, H. (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/cvpr52729.2023.02105 · Cited by 143
“Perception tasks in BEV including detection [34, 41, 43, 46,59,62], segmentation [30,43,55,79,88], and lane detection [4,11, 25] have been rapidly pushing the frontier of 3D vision for autonomous driving.”
BackgroundDeep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview
Fan, Z., Zhu, Y., He, Y., Sun, Q. L., Liu, H., & He, J. Y. D. (2022) · ACM Computing Surveys · doi:10.1145/3524496 · Cited by 123
“91 CaDDN [123] 2021 Pseudo-LiDAR Yes 23.”
BackgroundInfluentialOmni3D: A Large Benchmark and Model for 3D Object Detection in the Wild
Brazil, G., Kumar, A., Straub, J., Ravi, N., Johnson, J., & Gkioxari, G. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01264 · Cited by 111
“There is extensive work in the urban self-driving domain where the car class is at the epicenter [12, 17, 21, 23, 28, 43, 46, 51, 54, 59, 64, 65, 71, 77].”
BackgroundMilestones in Autonomous Driving and Intelligent Vehicles—Part II: Perception and Planning
Chen, L. F., Teng, S., Li, B., Na, X., Li, Y., Li, Z., Wang, J., Cao, D., Zheng, N., & Wang, F. (2023) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2023.3283021 · Cited by 112
“CaDDN [57] provides a fully differentiable end-to-end approach for combining depth estimation and object detection tasks.”
BackgroundCollaboration Helps Camera Overtake LiDAR in 3D Detection
Hu, Y., Lu, Y., Xu, R., Xie, W., Chen, S., & Wang, Y. (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/cvpr52729.2023.00892 · Cited by 103
GenAD: Generative End-to-End Autonomous Driving
Zheng, W., Song, R., Guo, X., Zhang, C., & Chen, L. F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73650-6_6 · Cited by 100
Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection
Yu, H., Dai, H., & Ding, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20080-9_6 · Cited by 98
“We inherit the depth loss from CaDDN [52] for backbone pre-training: Student Model.”
BackgroundMethodInfluentialFast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline
Li, Y., Huang, B., Chen, Z., Cui, Y., Liang, F., Shen, M., Liu, F., Xie, E., Sheng, L., Ouyang, W., et al. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3414835 · Cited by 101
“Moredetails are in Section III-D.”
Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving
Chen, Y., Dai, H., & Ding, Y. S. (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/cvpr52688.2022.00096 · Cited by 92
“pseudo point clouds and pseudo voxels, and then feed them to LiDAR-based 3D detectors, and the rest monocular 3D detection methods that use 2D feature learning from a single image with optional 3D cues matching, concatenating or guiding for 3D perception [24, 26, 31, 38, 39, 54, 57].”
MethodRevisiting Open World Object Detection
Zhao, X., Ma, Y., Wang, D., Shen, Y., Qiao, Y., & Liu, X. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3326279 · Cited by 98
“Deep learning models significantly promote the performance of object detection networks [2, 24], benefiting a wide range of applications, such as VQA [10, 14], visual reasoning [5, 8], and automatic driving [15].”
BackgroundDiversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection
Li, Z., Qu, Z., Zhou, Y., Liu, J., Wang, H., & Jiang, L. (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/cvpr52688.2022.00281 · Cited by 89
“Alternatively, it can also be converted to pseudo 3D point clouds firstly and then a LiDAR-based 3D detector is applied on them to derive the results [26,33,35].”
MethodOccWorld: Learning a 3D Occupancy World Model for Autonomous Driving
Zheng, W., Chen, W., Huang, Y., Zhang, B., Duan, Y., & Lu, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72624-8_4 · Cited by 152
DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection
Peng, L., Wu, X., Yang, Z., Li, X., & Cai, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19769-7_5 · Cited by 88
Multi-modality 3D object detection in autonomous driving: A review
Tang, Y., He, H., Wang, Y., Mao, Z., & Wang, H. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126587 · Cited by 92
MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries
Zhang, T., Chen, X., Wang, Y., Wang, Y., & Zhao, H. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00500 · Cited by 83
“Later CaDDN [24] and BEVDet [12] used similar represents for 3D detection.”
MethodMonoCD: Monocular 3D Object Detection with Complementary Depths
Yan, L., Yan, P., Xiong, S., Xiang, X., & Tan, Y. (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/cvpr52733.2024.00976 · Cited by 83
DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection
Kumar, A., Brazil, G., Corona, E., Parchami, A., & Liu, X. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20077-9_39 · Cited by 89
Far3D: Expanding the Horizon for Surround-View 3D Object Detection
Jiang, X., Li, S., Liu, Y., Wang, S., Jia, F., Wang, T., Han, L., & Zhang, X. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i3.28033 · Cited by 78
MonoGround: Detecting Monocular 3D Objects from the Ground
Qin, Z., & Li, X. (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/cvpr52688.2022.00377 · Cited by 82
“CaDDN [31] projects LiDAR point clouds into the image to create depth maps, then a categorical depth distribution is learned.”
BackgroundTS-BEV: BEV object detection algorithm based on temporal-spatial feature fusion
Dong, X., Shi, P., Qi, H., Yang, A., & Liang, T. (2024) · Displays · doi:10.1016/j.displa.2024.102814 · Cited by 76
MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection
Lian, Q., Li, P., & Chen, X. (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/cvpr52688.2022.00114 · Cited by 72
“Later work exploits from the perspective of network architecture [1, 21, 27], objective function [20, 30], etc.”
BackgroundBenchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection
Yu, K., Tang, T., Xie, H., Lin, Z., Liang, T., Wang, B., Chen, P., Hao, D., Wang, Y., & Liang, X. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00321 · Cited by 86
“3D detection has received extensive attention as one of the fundamental tasks in autonomous driving scenar-* ios [11,16,20,33,38,40,41,55,57,58].”
BackgroundMethodBird’s-Eye-View Scene Graph for Vision-Language Navigation
Liu, R., Wang, X., Wang, W., & Yang, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01007 · Cited by 80
“Motivated by the recent efforts that achieve learnable projection between BEV plane and perspective view [33– 35, 42, 43, 99–103], we collect oriented 3D bounding boxes in Matterport3D dataset [2] and perform camera-based BEV perception for embodied amodal detection [22, 104], as opposed to…”
MethodPseudo-Mono for Monocular 3D Object Detection in Autonomous Driving
Tao, C., Cao, J., Wang, C., Zhang, Z., & Gao, Z. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3237579 · Cited by 68
“Compared with the representative CaDDN [46] and DDMP-3D [49], the efficiency of AP 3D in Pseudo-Mono was improved by 8.24/5.16/4.7 and 7.7/5.79/6.36, respectively.”
MethodInfluentialStanding Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
Pang, Z., Li, J., Tokmakov, P., Chen, D., Zagoruyko, S., & Wang, Y.-X. (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/cvpr52729.2023.01719 · Cited by 72
FusionRCNN: LiDAR-Camera Fusion for Two-Stage 3D Object Detection
Xu, X., Dong, S., Xu, T., Ding, L., Wang, J., Jiang, P., Song, L., & Li, J. (2023) · Remote Sensing · doi:10.3390/rs15071839 · Cited by 75
LATR: 3D Lane Detection from Monocular Images with Transformer
Luo, Y., Zheng, C., Yan, X., Kun, T., Zheng, C., Cui, S., & Li, Z. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00730 · Cited by 64
“…there have been several attempts to leverage ground prior to facilitating 3D object detection, some make strong hypotheses like fixed ground [27], while others introduce extra prediction tasks, e.g ., dense depth estimation [46, 39, 35], horizon line detection, and contact points detection [50].”
BackgroundMVFusion: Multi-View 3D Object Detection with Semantic-aligned Radar and Camera Fusion
Wu, Z., Chen, G., Gan, Y., Wang, L., & Pu, J. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161329 · Cited by 79
“Then cameras achieve more affordable cost and provide abundant semantic information, though lacking depth information, which also attract extensive attention [1], [24]–[26], such as monocular 3D object detection [19], [20], [27] and multi-view 3D object detection [13], [14], [25], [28].”
BackgroundMonocular 3D Object Detection with Depth from Motion
Wang, T., Pang, J., & Lin, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20077-9_23 · Cited by 67
CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection
Hwang, J.-J., Kretzschmar, H., Manela, J., Rafferty, S., Armstrong-Crews, N., Chen, T., & Anguelov, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19839-7_23 · Cited by 63
Learning Ego 3D Representation as Ray Tracing
Lu, J., Zhou, Z., Zhu, X., Xu, H., & Zhang, L. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19809-0_8 · Cited by 63
Communication-Efficient Collaborative Perception via Information Filling with Codebook
Hu, Y., Peng, J., Liu, S., Ge, J., Liu, S., & Chen, S. (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/cvpr52733.2024.01466 · Cited by 76
“We adopt PointPillar [13] and CaDDN [23] for the LiDAR and camera detector, respectively.”
MethodTerrainNet: Visual Modeling of Complex Terrain for High-speed, Off-road Navigation
Meng, X., Hatch, N., Lambert, A. S., Li, A., Wagener, N., Schmittle, M., Lee, J., Yuan, W., Chen, Z., Deng, S., et al. (2023) · Robotics: Science and Systems · doi:10.15607/rss.2023.xix.103 · Cited by 58
CAPE: Camera View Position Embedding for Multi-View 3D Object Detection
Xiong, K., Gong, S., Ye, X., Tan, X. Y., Wan, J., Ding, E., Wang, J., & Bai, X. (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/cvpr52729.2023.02066 · Cited by 58
“Depth-guided methods need extra data sources such as point clouds and depth images in the training phase [7, 28, 36, 37, 50].”
BackgroundHomogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection
Li, X. Y., Shi, B., Hou, Y., Wu, X., Ma, T., Li, Y., & He, L. J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19839-7_40 · Cited by 59
Visual Point Cloud Forecasting Enables Scalable Autonomous Driving
Yang, Z., Chen, L., Sun, Y., & Li, H. (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/cvpr52733.2024.01390 · Cited by 82
Zou, Z., Ye, X., Du, L., Cheng, X., Tan, X., Li, Z., Feng, J., Xue, X., & Ding, E. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00271 · Cited by 54
“Note that the proposed DFR-Net (I+D) can get a real-time speed of 40 FPS on Tesla V100, which is 20 times faster than CaDNN [25].”
BackgroundResultLidar Point Cloud Guided Monocular 3D Object Detection
Peng, L., Liu, F., Yu, Z., Yan, S., Deng, D., Yang, Z., Liu, H., & Cai, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19769-7_8 · Cited by 53
Uncertainty-Aware Vision-Based Metric Cross-View Geolocalization
Fervers, F., Bullinger, S., Bodensteiner, C., Arens, M., & Stiefelhagen, R. (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/cvpr52729.2023.02071 · Cited by 53
“point-cloud or voxelmap) for the projection [31, 32, 41].”
Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., & Zhao, F. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547859 · Cited by 62
“external depth estimation network [37, 45, 53] or incorporate prior visual knowledge [22, 27].”
BackgroundGao, H., Yu, X., Xu, Y., Kim, J., & Wang, Y. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3353530 · Cited by 54
“CaDDN [20] generates a birds-eye view (BEV) representation by training a depth estimation subnetwork to learn the categorical depth distribution of each pixel.”
BackgroundMethodResultInfluentialBEV perception for autonomous driving: State of the art and future perspectives
Zhao, J., Shi, J., & Li, Z. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125103 · Cited by 62
Fully Sparse Fusion for 3D Object Detection
Li, Y., Fan, L., Liu, Y., Huang, Z., Chen, Y., Wang, N., & Zhang, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3392303 · Cited by 62
“BEV-based methods [43, 29] lift 2D features to 3D [38, 19, 26] or using transformer-like structures [29, 57, 50] to construct BEV feature map for prediction.”
MethodSuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation
Dong, H., Gu, W., Zhang, X., Xu, J., Ai, R., Lu, H., Kannala, J., & Chen, X. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611320 · Cited by 51
“Our proposed depth-aware camera-to-BEV module differs from the existing depth prediction methods [28], [29].”
MethodYang, L., Zhang, X., Li, J., Wang, L., Zhu, M., Zhang, C., & Liu, H. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3270728 · Cited by 50
“Another keypoint-based works [25], [40], [41], [42], [43], [44], [45], [46] directly estimate the 3D properties of the instance based on the high-dimensional features at the keypoint position.”
BackgroundMatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception
Zhou, H., Ge, Z., Li, Z., & Zhang, X. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00785 · Cited by 51
“CaDDN [18] proposes treating depth prediction as a classification task rather than a regression task, and projecting image feature into Bird’s-Eye-View (BEV) space to achieve unified modeling of detection and depth prediction.”
BackgroundMethodInfluentialHomography Loss for Monocular 3D Object Detection
Gu, J., Wu, B., Fan, L., Huang, J., Cao, S., Xiang, Z., & Hua, X. (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/cvpr52688.2022.00115 · Cited by 48
“When compared with stereo images [15] or LiDAR-based methods [23, 27, 30, 32, 39, 40], in some earlier works, auxiliary information are necessary for monocular 3D detection to achieve competitive results.”
MethodBEVHeight++: Toward Robust Visual Centric 3D Object Detection
Yang, L., Tang, T., Li, J., Yuan, K., Wu, K. F., Chen, P., Wang, L., Huang, Y., Li, L., Zhang, X., et al. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3549711 · Cited by 48
MonoGAE: Roadside Monocular 3D Object Detection With Ground-Aware Embeddings
Yang, L., Zhang, X., Yu, J., Li, J., Zhao, T., Wang, L., Huang, Y., Zhang, C., Wang, H., & Li, Y. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3412759 · Cited by 52
“…knowledge can be obtained through diverse avenues, including the generation of a depth map through LiDAR point cloud (or Pseudo-LiDAR) techniques [27], [40], utilization of monocular depth prediction models [10], [23], or the generation of a disparity map via stereo cameras [20]. iii ) Pure…”
MethodLin, C., Tian, D., Duan, X., Zhou, J., Zhao, D., & Cao, D. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3171553 · Cited by 50
“CaDNN [26] is a differentiable end-to-end approach for monocular 3D detection that predicts categorical depth distribution for each pixel.”
BackgroundKlingner, M., Borse, S., Kumar, V. R., Rezaei, B., Narayanan, V., Yogamani, S. K., & Porikli, F. (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/cvpr52729.2023.01282 · Cited by 53
“Existing solutions to 3DOD are mainly based on extracting a unified representation from multiple cameras [28,30,37,41] such as the bird’s-eye view (BEV) grid.”
BackgroundCOTR: Compact Occupancy TRansformer for Vision-Based 3D Occupancy Prediction
Ma, Q., Tan, X., Qu, Y., Ma, L., Zhang, Z., & Xie, Y. (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/cvpr52733.2024.01884 · Cited by 45
“…broadly categorized into two types: one relies on explicit depth estimation to form a pseudo point cloud and construct the 3D space [8, 16, 20, 26, 27], while the other pre-defines the BEV space and implicitly models the depth information through spatial cross-attention [11, 18, 35, 36, 40],…”
BackgroundMonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer
Zhou, Y., Zhu, H., Liu, Q., Chang, S., & Guo, M. (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/cvpr52729.2023.01678 · Cited by 45
“Current Mono3D methods, such as depth map based [15, 29, 36], pseudo-LiDAR based [15, 29–31, 36, 54, 57], and image-only based [2,3,12,22,26,28,42,48,51,64–67], mostly follow the pipelines of traditional 2D object detectors [41, 42, 48, 66] to first localize object centers from heatmaps and then aggregate visual featu…”
MethodInfluentialMonoNeRD: NeRF-like Representations for Monocular 3D Object Detection
Xu, J., Peng, L., Chen, H., Li, H., Qian, W., Li, K., Wang, W., & Cai, D. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00627 · Cited by 43
Densely Constrained Depth Estimator for Monocular 3D Object Detection
Li, Y., Chen, Y., He, J., & Zhang, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20077-9_42 · Cited by 42
SGM3D: Stereo Guided Monocular 3D Object Detection
Zhou, Z., Du, L., Ye, X., Zou, Z., Tan, X., Zhang, L., Xue, X., & Feng, J. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3191849 · Cited by 42
“Inspired by LSS [37] and CaDDN [15], in the image-assisted BEV encoder of the monocular branch (Sec.”
MethodRadar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey
Shi, K., He, S., Shi, Z., An-jun, C., Xiong, Z., Chen, J., & Luo, J. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3599596 · Cited by 62
“B ASED O BJECT D ETECTION depth estimation interaction [306] to aid in 3D object detection.”
Metadata
- Authors
- Reading, C., Harakeh, A., Chae, J., & Waslander, S. L.
- Affiliations
- University of Toronto (CA)
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 8551-8560
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3133598367
- Cited by
- 595
- References
- 82
- Citations by year
- 2026: 57 · 2025: 143 · 2024: 173 · 2023: 136 · 2022: 73 · 2021: 13
- FWCI
- 32.30
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- 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 › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Keywords
- monocular 3D object detection, depth estimation, single-stage detectors, autonomous driving, Waymo Open Dataset, KITTI dataset
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
