Towards Part-Based Understanding of RGB-D Scans

Abstract

Recent advances in 3D semantic scene understanding have shown impressive progress in 3D instance segmentation, enabling object-level reasoning about 3D scenes; however, a finer-grained understanding is required to enable interactions with objects and their functional understanding. Thus, we propose the task of part-based scene understanding of real-world 3D environments: from an RGB-D scan of a scene, we detect objects, and for each object predict its decomposition into geometric part masks, which composed together form the complete geometry of the observed object. We leverage an intermediary part graph representation to enable robust completion as well as building of part priors, which we use to construct the final part mask predictions. Our experiments demonstrate that guiding part understanding through part graph to part prior-based predictions significantly outperforms alternative approaches to the task of semantic part completion.

Resources

Fulltext PDF: Towards Part-Based Understanding of RGB-D Scans
Supplementary PDF: Towards Part-Based Understanding of RGB-D Scans Supplementary Materials
Source code: https://github.com/alexeybokhovkin/part-based-scan-understanding
Video Video
Slides: Slides
Official project page: https://www.3dunderstanding.org/papers/2021/bokhovkin2021towards/

Citing:

@inproceedings{2021-towards-part-based,
 author = {Bokhovkin, Alexey and Ishimtsev, Vladislav and Bogomolov, Emil and Zorin, Denis and Artemov, Alexey and Burnaev, Evgeny and Dai, Angela},
 booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
 month = {June},
 pages = {7484-7494},
 title = {Towards Part-Based Understanding of RGB-D Scans},
 year = {2021}
}

Alexey Bokhovkin	Vladislav Ishimtsev	Emil Bogomolov	Denis Zorin
Alexey Artemov	Evgeny Burnaev	Angela Dai

Towards Part-Based Understanding of RGB-D Scans

Abstract

Video

Resources