Delving into Localization Errors for Monocular 3D Object Detection
Open accessThe DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Abstract
Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging. In this work, by intensive diagnosis experiments, we quantify the impact introduced by each sub-task and found the ‘localization error’ is the vital factor in restricting monocular 3D detection. Besides, we also investigate the underlying reasons behind localization errors, analyze the issues they might bring, and propose three strategies. First, we revisit the misalignment between the center of the 2D bounding box and the projected center of the 3D object, which is a vital factor leading to low localization accuracy. Second, we observe that accurately localizing distant objects with existing technologies is almost impossible, while those samples will mislead the learned network. To this end, we propose to remove such samples from the training set for improving the overall performance of the detector. Lastly, we also propose a novel 3D IoU oriented loss for the size estimation of the object, which is not affected by ‘localization error’. We conduct extensive experiments on the KITTI dataset, where the proposed method achieves real-time detection and outperforms previous methods by a large margin. The code will be made available at: https://github.com/xinzhuma/monodle.
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
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
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
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 · cited 1×
“We evaluate our method on the challenging KITTI dataset [14, 15], which provides 7,481 images for training and 7,518 images for testing.”
MethodVision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 1×
“We evaluate our method on the challenging KITTI dataset [14, 15], which provides 7,481 images for training and 7,518 images for testing.”
MethodDeformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513 · cited 1×
“Compared with MonoPair, which shares a similar framework as ours, our method can still save 16 ms for one image in the inference phase, mainly because: 1) we use standard DLA-34 as our backbone, instead of modified DL4-34 with DCN [11, 45].”
MethodGeneralized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00075 · Cited by 6,612
VoxelNet: 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
PointPillars: 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
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
Multi-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
Cited by
3D 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 450
Self-citationGeometry 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
Self-citationRCBEVDet: 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
3D 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
Self-citationCRAFT: 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
Omni3D: 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
Object Detection with Transformers: A Review
Shehzadi, T., Hashmi, K. A., Liwicki, M., Stricker, D., & Afzal, M. Z. (2025) · Sensors · doi:10.3390/s25196025 · Cited by 93
LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection
Hung, W.-C., Casser, V., Kretzschmar, H., Hwang, J.-J., & Anguelov, D. (2024) · 2024 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra57147.2024.10609986 · Cited by 33
“As pointed out by Ma et al. [55], the performance of monocular camera 3D detection methods can be greatly improved when their longitudinal localization errors are mitigated by using ground truth depth or localization.”
BackgroundRay denoising: Depth-aware hard negative sampling for multi-view 3d object detection
Liu, F., Huang, T., Zhang, Q., Yao, H., Zhang, C., Wan, F., Ye, Q., & Zhou, Y. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72967-6_12 · Cited by 33
Metadata
- Authors
- Ma, X., Zhang, Y., Xu, D., Zhou, D., Yi, S., Li, H., & Ouyang, W.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 4719-4728
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3169690993
- Cited by
- 268
- References
- 46
- FWCI
- 15.51
- 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.