CoChat

Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing

Li, Chi, Zia, M. Zeeshan, Tran, Quoc-Huy, Yu, Xiang, Hager, Gregory D., Chandraker, Manmohan · 2017 · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 82

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Abstract

Monocular 3D object parsing is highly desirable in various scenarios including occlusion reasoning and holistic scene interpretation. We present a deep convolutional neural network (CNN) architecture to localize semantic parts in 2D image and 3D space while inferring their visibility states, given a single RGB image. Our key insight is to exploit domain knowledge to regularize the network by deeply supervising its hidden layers, in order to sequentially infer intermediate concepts associated with the final task. To acquire training data in desired quantities with ground truth 3D shape and relevant concepts, we render 3D object CAD models to generate large-scale synthetic data and simulate challenging occlusion configurations between objects. We train the network only on synthetic data and demonstrate state-of-the-art performances on real image benchmarks including an extended version of KITTI, PASCAL VOC, PASCAL3D+ and IKEA for 2D and 3D keypoint localization and instance segmentation. The empirical results substantiate the utility of our deep supervision scheme by demonstrating effective transfer of knowledge from synthetic data to real images, resulting in less overfitting compared to standard end-to-end training.

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.

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

Integrity signals

Registry

Crossref · 10.1109/cvpr.2017.49

Cites

7 of 7 references verified0 citation errors · 0 not checkable

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.

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

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

Show all 7 references

Research works printed but not linked: 38

  1. 10.1109/CVPR.2015.7298800 · DOI · Paper page
  2. 10.1109/TPAMI.2015.2497699 · DOI · Paper page
  3. 10.1109/ICCV.2015.308 · DOI · Paper page
  4. smith, 1986, Perception of Organization in a Random Stimulus
  5. simonyan, 2014, Very Deep Convolutional Networks for Large-scale Image Recognition
  6. 10.1109/34.857006 · DOI · Paper page
  7. 10.1007/978-3-319-46466-4_22 · DOI
  8. 10.1109/CVPR.2015.7298758 · DOI · Paper page
  9. torresani, 2003, Learning nonrigid 3d shape from 2d motion, Advances in neural information processing systems
  10. ioffe, 2015, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, JMLR
  11. 10.1109/WACV.2014.6836101 · DOI · Paper page
  12. jia, 2014, Caffe Convolutional Architecture for Fast Feature Embedding
  13. 10.1109/CVPR.2016.354 · DOI · Paper page
  14. 10.1109/CVPR.2015.7298807 · DOI · Paper page
  15. kulkarni, 2015, Deep convolutional inverse graphics network, NIPS
  16. lee, 2015, Deeply-Supervised Nets, AISTATS
  17. lee, 1985, Determination of 3D human body postures from a single view, CVGIP
  18. 10.1007/978-3-319-10599-4_31 · DOI
  19. rezende, 2016, Unsupervised learning of 3d structure from images, NIPS
  20. choy, 2016, 3DR2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction, ECCV
  21. pepik, 2013, Occlusion patterns for object class detection, CVPR
  22. 10.1109/CVPR.2012.6248074 · DOI · Paper page
  23. glorot, 2010, Understanding the difficulty of training deep feedforward neural networks, AISTATS
  24. 10.1109/CVPR.2014.81 · DOI · Paper page
  25. gupta, 2015, Inferring 3d object pose in rgb-d images
  26. 10.1109/CVPR.2014.487 · DOI · Paper page
  27. long, 2014, Do convnets learn correspondence?, NIPS
  28. 10.1007/s11263-014-0780-y · DOI
  29. marr, 1982, Vision
  30. 10.1007/978-1-4613-2551-2 · DOI · Paper page
  31. 10.1007/978-3-319-46454-1_4 · DOI
  32. 10.1109/34.42852 · DOI · Paper page
  33. 10.1109/CVPR.2011.5995741 · DOI · Paper page
  34. massa, 2015, Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views, CVPR
  35. zia, 2009, Acquisition of a Dense 3D Model Database for Robotic Vision, ICAR
  36. 10.1109/CVPR.2015.7298639 · DOI · Paper page
  37. 10.1109/CVPR.2016.20 · DOI · Paper page
  38. moreno, 2016, Overcoming occlusion with inverse graphics, ECCV

Cited by

Metadata

Authors
Li, C., Zia, M. Z., Tran, Q.-H., Yu, X., Hager, G. D., & Chandraker, M.
Venue
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2017-07
Pages
388-397
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2964057995
Cited by
82
References
7
FWCI
3.72
Type
conference paper
Language
en
Open access
closed

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.