Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
6-2023
Abstract
Semantic Scene Completion (SSC) transforms an image of single-view depth and/or RGB 2D pixels into 3D voxels, each of whose semantic labels are predicted. SSC is a well-known ill-posed problem as the prediction model has to “imagine” what is behind the visible surface, which is usually represented by Truncated Signed Distance Function (TSDF). Due to the sensory imperfection of the depth camera, most existing methods based on the noisy TSDF estimated from depth values suffer from 1) incomplete volumetric predictions and 2) confused semantic labels. To this end, we use the ground-truth 3D voxels to generate a perfect visible surface, called TSDF-CAD, and then train a “cleaner” SSC model. As the model is noise-free, it is expected to focus more on the “imagination” of unseen voxels. Then, we propose to distill the intermediate “cleaner” knowledge into another model with noisy TSDF input. In particular, we use the 3D occupancy feature and the semantic relations of the “cleaner self” to supervise the counterparts of the “noisy self” to respectively address the above two incorrect predictions. Experimental results validate that the proposed method improves the noisy counterparts with 3.1% IoU and 2.2% mIoU for measuring scene completion and SSC separately, and also achieves a new state-of-the-art performance on the popular NYU dataset.
Discipline
Databases and Information Systems | Graphics and Human Computer Interfaces
Research Areas
Data Science and Engineering
Publication
Proceedings of the 2023 Conference on Computer Vision and Pattern Recognition, Vancouver, Canada, 2023 June 18-22
First Page
867
Last Page
877
Identifier
10.48550/arXiv.2303.09977
Publisher
CVPR
City or Country
Vancouver
Citation
WANG, Fengyun; ZHANG, Dong; ZHANG, Hanwang; TANG, Jinhui; and SUN, Qianru.
Semantic scene completion with cleaner self. (2023). Proceedings of the 2023 Conference on Computer Vision and Pattern Recognition, Vancouver, Canada, 2023 June 18-22. 867-877.
Available at: https://ink.library.smu.edu.sg/sis_research/8100
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/ 10.48550/arXiv.2303.09977
Included in
Databases and Information Systems Commons, Graphics and Human Computer Interfaces Commons