Resolution-switchable 3D Semantic Scene Completion

Luo, Shoutong; Sun, Zhengxing; Sun, Yunhan; Wang, Yi

Resolution-switchable 3D Semantic Scene Completion

Files

v41i7pp121-130.pdf (3.99 MB)

Date

2022

Authors

Luo, Shoutong
Sun, Zhengxing
Sun, Yunhan
Wang, Yi

Publisher

The Eurographics Association and John Wiley & Sons Ltd.

Abstract

Semantic scene completion (SSC) aims to recover the complete geometric structure as well as the semantic segmentation results from partial observations. Previous works could only perform this task at a fixed resolution. To handle this problem, we propose a new method that can generate results at different resolutions without redesigning and retraining. The basic idea is to decouple the direct connection between resolution and network structure. To achieve this, we convert feature volume generated by SSC encoders into a resolution adaptive feature and decode this feature via point. We also design a resolution-adapted point sampling strategy for testing and a category-based point sampling strategy for training to further handle this problem. The encoder of our method can be replaced by existing SSC encoders. We can achieve better results at other resolutions while maintaining the same accuracy as the original resolution results. Code and data are available at https://github.com/lstcutong/ReS-SSC.

CCS Concepts: Computing methodologies → Volumetric models

        @article{10.1111:cgf.14662
,
journal = {Computer Graphics Forum},
title = {{Resolution-switchable 3D Semantic Scene Completion
}},
author = {Luo, Shoutong and 
Sun, Zhengxing and 
Sun, Yunhan and 
Wang, Yi
},
year = {2022
},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.14662
}
}