Towards Generalization Across Depth for Monocular 3D Object Detection
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
While expensive LiDAR and stereo camera rigs have enabled the development of successful 3D object detection methods, monocular RGB-only approaches lag much behind. This work advances the state of the art by introducing MoVi-3D, a novel, single-stage deep architecture for monocular 3D object detection. MoVi-3D builds upon a novel approach which leverages geometrical information to generate, both at training and test time, virtual views where the object appearance is normalized with respect to distance. These virtually generated views facilitate the detection task as they significantly reduce the visual appearance variability associated to objects placed at different distances from the camera. As a consequence, the deep model is relieved from learning depth-specific representations and its complexity can be significantly reduced. In particular, in this work we show that, thanks to our virtual views generation process, a lightweight, single-stage architecture suffices to set new state-of-the-art results on the popular KITTI3D benchmark.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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
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 73,472
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
CornerNet: Detecting Objects as Paired Keypoints
Law, H., & Deng, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_45 · Cited by 3,852
PointRCNN: 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
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01247-4 · Cited by 2,965 · cited 1×
“In the last decade, thanks to the emergence of deep neural networks and to the availability of large-scale annotated datasets, the state of the art in 2D object detection has improved significantly [25,18,23,24,15,11], reaching near-human performance [16].”
BackgroundDeep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2018) · arXiv · doi:10.48550/arxiv.1809.02165 · Cited by 2,965
MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
Chen, T., Li, M., Li, Y., Lin, M., Wang, N., Wang, M., Xiao, T., Xu, B., Zhang, C., & Zhang, Z. (2015) · arXiv · doi:10.48550/arxiv.1512.01274 · Cited by 1,819
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017) · arXiv · doi:10.48550/arxiv.1708.02002 · Cited by 1,227
Wang, Y., Chao, W.-L., Garg, D., Hariharan, B., Campbell, M., & Weinberger, K. Q. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00864 · Cited by 1,154 · cited 1×
“Pseudo-Lidar [33] takes advantage of pre-computed depth maps to convert RGB images to 3D point clouds.”
3D Bounding Box Estimation Using Deep Learning and Geometry
Mousavian, A., Anguelov, D., Flynn, J., & Kosecka, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.597 · Cited by 1,129 · cited 1×
“Deep3DBox [21] proposes to estimate the full 3D pose and the dimensions of objects from 2D bounding boxes by considering projective geometry constraints.”
BackgroundMonocular 3D Object Detection for Autonomous Driving
Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., & Urtasun, R. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.236 · Cited by 1,019 · cited 1×
“Mono3D [4] generates 3D candidate boxes and scores them according to semantic segmentation, contextual, shape and class-specific features.”
BackgroundMulti-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 · cited 1×
“Unsurprisingly, state-of-the-art 3D detection methods exploit a multi-modal approach, combining data from RGB images with LiDAR information [13,34,31,30].”
BackgroundM3D-RPN: Monocular 3D Region Proposal Network for Object Detection
Brazil, G., & Liu, X. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00938 · Cited by 591
Disentangling Monocular 3D Object Detection
Simonelli, A., Bulo, S. R., Porzi, L., Lopez-Antequera, M., & Kontschieder, P. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00208 · Cited by 520
Self-citationMonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization
Qin, Z., Wang, J., & Lu, Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018851 · Cited by 290
RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement
Shin, K., Kwon, Y. P., & Tomizuka, M. (2019) · 2019 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2019.8813895 · Cited by 221 · cited 1×
“Unsurprisingly, state-of-the-art 3D detection methods exploit a multi-modal approach, combining data from RGB images with LiDAR information [13,32,29,28].”
BackgroundOrthographic feature transform for monocular 3d object detection
Roddick, T., Kendall, A., & Cipolla, R. (2018) · arXiv · doi:10.48550/arxiv.1811.08188 · Cited by 211 · cited 1×
“OFTNet [26] proposes a so-called Orthographic Feature Transform which translates the RGB 2D information in a 3D voxel map.”
Method
Cited by
Categorical Depth Distribution Network for Monocular 3D Object Detection
Reading, C., Harakeh, A., Chae, J., & Waslander, S. L. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00845 · Cited by 595
Objects are Different: Flexible Monocular 3D Object Detection
Zhang, Y., Lu, J., & Zhou, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00330 · Cited by 306
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) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00310 · Cited by 264
Geometry-based Distance Decomposition for Monocular 3D Object Detection
Shi, X., Ye, Q., Chen, X., Chen, C., Chen, Z., & Kim, T.-K. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01489 · Cited by 158
“ods [50, 7, 41, 42] directly learn a mapping from input images to the distance.”
BackgroundMethodInfluentialRCBEVDet: Radar-Camera Fusion in Bird's Eye View for 3D Object Detection
Lin, Z., Liu, Z., Xia, Z., Wang, X., Wang, Y., Qi, S., Dong, Y., Dong, N., Zhang, L., & Zhu, C. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01414 · Cited by 153
“These efforts include inferring depth from images [45], utilizing geometric constraints and shape priors [27], design specific loss functions [29, 36], and exploring joint 3D detection and reconstruction optimization [21].”
Method
Metadata
- Authors
- Simonelli, A., Buló, S. R., Porzi, L., Ricci, E., & Kontschieder, P.
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2020
- Pages
- 767-782
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W3014575704
- Cited by
- 70
- References
- 19
- FWCI
- 3.89
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.