CoChat
Sign Up
Cited by 251Advanced Neural Network Applications3D Shape Modeling and AnalysisAdvanced Vision and Imaging

ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

Open access
Rukhovich, Danila, Vorontsova, Anna, Konushin, Anton·2022·2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
DOI 10.1109/wacv51458.2022.00133
Open this paper in CoChat — free accountOpen PDF

Abstract

In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem. To address this problem, we propose ImVoxel-Net, a novel fully convolutional method of 3D object detection based on posed monocular or multi-view RGB images. The number of monocular images in each multi-view input can variate during training and inference; actually, this number might be unique for each multi-view input. ImVoxelNet successfully handles both indoor and outdoor scenes, which makes it general-purpose. Specifically, it achieves state-of-the-art results in car detection on KITTI (monocular) and nuScenes (multi-view) benchmarks among all methods that accept RGB images. Moreover, it surpasses existing RGB-based 3D object detection methods on the SUN RGB-D dataset. On ScanNet, ImVoxelNet sets a new benchmark for multi-view 3D object detection. The source code and the trained models are available at https://github.com/saic-vul/imvoxelnet.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/wacv51458.2022.00133

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Gemini 2.0's 3D detection performance is comparable to existing state-of-the-art expert models.

    “Gemini 2.0's 3D detection performance is comparable to existing state-of-the-art expert models”

    From Gemini Robotics: Bringing AI into the Physical World (2025) · cites this paper as Rukhovich et al., 2022

    Section 4.3 (Results, pp. 6–8) compares ImVoxelNet with other 3D detectors, but does not evaluate Gemini 2.0. Searches for “Gemini 2.0” and “Gemini expert models” found no passage supporting the claimed performance comparison. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 35

  1. [1][1] W. Bao, B. Xu, and Z. Chen. Monofenet: Monocular 3d object detection with feature enhancement networks. IEEE Transactions on Image Processing, 29:2753–2765, 2019.
  2. [2][2] G. Brazil and X. Liu. M3d-rpn: Monocular 3d region pro- posal network for object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9287–9296, 2019.
  3. [4][4] F. Chabot, M. Chaouch, J. Rabarisoa, C. Teuliere, and T. Chateau. Deep manta: A coarse-to-fine many-task net- work for joint 2d and 3d vehicle analysis from monocular image. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2040–2049, 2017.
  4. [5][5] K. Chen, J. Wang, J. Pang, Y. Cao, Y. Xiong, X. Li, S. Sun, W. Feng, Z. Liu, J. Xu, et al. Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155, 2019. · arXiv
  5. [6][6] X. Chen, K. Kundu, Y. Zhu, A. G. Berneshawi, H. Ma, S. Fi- dler, and R. Urtasun. 3d object proposals for accurate object class detection. In Advances in Neural Information Process- ing Systems, pages 424–432. Citeseer, 2015.
  6. [7][7] X. Chen, K. Kundu, Z. Zhang, H. Ma, S. Fidler, and R. Urta- sun. Monocular 3d object detection for autonomous driving. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2147–2156, 2016.
  7. [8][8] W. Choi, Y.-W. Chao, C. Pantofaru, and S. Savarese. Under- standing indoor scenes using 3d geometric phrases. In Pro- ceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 33–40, 2013.
  8. [9][9] A. Dai, A. X. Chang, M. Savva, M. Halber, T. Funkhouser, and M. Nießner. Scannet: Richly-annotated 3d reconstruc- tions of indoor scenes. In Proceedings of the IEEE Con- ference on Computer Vision and Pattern Recognition, pages 5828–5839, 2017.
  9. [10][10] M. Ding, Y. Huo, H. Yi, Z. Wang, J. Shi, Z. Lu, and P. Luo. Learning depth-guided convolutions for monocular 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 1000–1001, 2020.
  10. [11][11] A. Geiger, P. Lenz, and R. Urtasun. Are we ready for au- tonomous driving? the kitti vision benchmark suite. In 2012 IEEE Conference on Computer Vision and Pattern Recogni- tion, pages 3354–3361. IEEE, 2012.
  11. [13][13] J. Hou, A. Dai, and M. Nießner. 3d-sis: 3d semantic instance segmentation of rgb-d scans. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4421–4430, 2019.
  12. [14][14] S. Huang, S. Qi, Y. Xiao, Y. Zhu, Y. N. Wu, and S.-C. Zhu. Cooperative holistic scene understanding: Unifying 3d ob- ject, layout, and camera pose estimation. arXiv preprint arXiv:1810.13049, 2018. · arXiv
  13. [15][15] S. Huang, S. Qi, Y. Zhu, Y. Xiao, Y. Xu, and S.-C. Zhu. Holistic 3d scene parsing and reconstruction from a single rgb image. In Proceedings of the European Conference on Computer Vision (ECCV), pages 187–203, 2018.
  14. [16][16] S. Huang, Y. Chen, T. Yuan, S. Qi, Y. Zhu, and S.-C. Zhu. Perspectivenet: 3d object detection from a single rgb im- age via perspective points. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, ed- itors, Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019.
  15. [17][17] M. Jaritz, J. Gu, and H. Su. Multi-view pointnet for 3d scene understanding. In Proceedings of the IEEE/CVF Interna- tional Conference on Computer Vision Workshops, pages 0– 0, 2019.
  16. [18][18] A. Kundu, Y. Li, and J. M. Rehg. 3d-rcnn: Instance-level 3d object reconstruction via render-and-compare. In Proceed- ings of the IEEE conference on computer vision and pattern recognition, pages 3559–3568, 2018.
  17. [20][20] B. Li, W. Ouyang, L. Sheng, X. Zeng, and X. Wang. Gs3d: An efficient 3d object detection framework for au- tonomous driving. In Proceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition, pages 1019–1028, 2019.
  18. [21][21] P. Li, X. Chen, and S. Shen. Stereo r-cnn based 3d ob- ject detection for autonomous driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7644–7652, 2019.
  19. [22][22] P. Li, H. Zhao, P. Liu, and F. Cao. Rtm3d: Real-time monoc- ular 3d detection from object keypoints for autonomous driv- ing. arXiv preprint arXiv:2001.03343, 2, 2020. · arXiv
  20. [23][23] Z. Liu, Z. Wu, and R. Tóth. Smoke: single-stage monocular 3d object detection via keypoint estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition Workshops, pages 996–997, 2020. 9
  21. [24][24] X. Ma, Z. Wang, H. Li, P. Zhang, W. Ouyang, and X. Fan. Accurate monocular 3d object detection via color-embedded 3d reconstruction for autonomous driving. In Proceedings of the IEEE/CVF International Conference on Computer Vi- sion, pages 6851–6860, 2019.
  22. [25][25] A. Mousavian, D. Anguelov, J. Flynn, and J. Kosecka. 3d bounding box estimation using deep learning and geometry. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 7074–7082, 2017.
  23. [26][26] Z. Murez, T. van As, J. Bartolozzi, A. Sinha, V. Badri- narayanan, and A. Rabinovich. Atlas: End-to-end 3d scene reconstruction from posed images. arXiv preprint arXiv:2003.10432, 2020. · arXiv
  24. [27][27] Y. Nie, X. Han, S. Guo, Y. Zheng, J. Chang, and J. J. Zhang. Total3dunderstanding: Joint layout, object pose and mesh re- construction for indoor scenes from a single image. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 55–64, 2020.
  25. [29][29] C. R. Qi, O. Litany, K. He, and L. J. Guibas. Deep hough vot- ing for 3d object detection in point clouds. In Proceedings of the IEEE/CVF International Conference on Computer Vi- sion, pages 9277–9286, 2019.
  26. [30][30] C. R. Qi, X. Chen, O. Litany, and L. J. Guibas. Imvotenet: Boosting 3d object detection in point clouds with image votes. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4404–4413, 2020.
  27. [31][31] Z. Qin, J. Wang, and Y. Lu. Monogrnet: A geometric rea- soning network for monocular 3d object localization. In Pro- ceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 8851–8858, 2019.
  28. [32][32] Z. Qin, J. Wang, and Y. Lu. Triangulation learning network: from monocular to stereo 3d object detection. In Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7615–7623, 2019.
  29. [33][33] T. Roddick, A. Kendall, and R. Cipolla. Orthographic feature transform for monocular 3d object detection. arXiv preprint arXiv:1811.08188, 2018. · arXiv
  30. [35][35] A. Simonelli, S. R. Bulo, L. Porzi, M. L. Antequera, and P. Kontschieder. Disentangling monocular 3d object detec- tion: From single to multi-class recognition. IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 2020.
  31. [36][36] V. A. Sindagi, Y. Zhou, and O. Tuzel. Mvx-net: Multimodal voxelnet for 3d object detection. In 2019 International Con- ference on Robotics and Automation (ICRA), pages 7276– 7282. IEEE, 2019.
  32. [39][39] Y. Yan, Y. Mao, and B. Li. Second: Sparsely embedded convolutional detection. Sensors, 18(10):3337, 2018.
  33. [40][40] S. Zhang, C. Chi, Y. Yao, Z. Lei, and S. Z. Li. Bridg- ing the gap between anchor-based and anchor-free detection via adaptive training sample selection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9759–9768, 2020.
  34. [41][41] Z. Zhang, B. Sun, H. Yang, and Q. Huang. H3dnet: 3d object detection using hybrid geometric primitives. In European Conference on Computer Vision, pages 311–329. Springer, 2020.
  35. [42][42] D. Zhou, J. Fang, X. Song, C. Guan, J. Yin, Y. Dai, and R. Yang. Iou loss for 2d/3d object detection. In 2019 In- ternational Conference on 3D Vision (3DV), pages 85–94. IEEE, 2019. 10

Cited by

Sorted by citations

Authors
Rukhovich, D., Vorontsova, A., & Konushin, A.
Affiliations
  • Lomonosov Moscow State University (RU)
  • Samsung (Russia) (RU)
ORCID
Konushin, Anton
Venue
2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Publisher
IEEE
Published
2022-01
Pages
1265-1274
ISSN
2472-6737 (ISSN-L)
DOI
10.1109/wacv51458.2022.00133
OpenAlex
W3171032126
Cited by
251
References
7
Citations by year
2026: 40 · 2025: 72 · 2024: 63 · 2023: 58 · 2022: 16 · 2021: 2
FWCI
18.48
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE Winter Conference on Applications of Computer Vision (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
Keywords
3D object detection, monocular RGB, fully convolutional network, end-to-end optimization, car detection, indoor and outdoor scenes, KITTI, nuScenes, SUN RGB-D, ScanNet

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