March 26, 2024, 4:48 a.m. | Laiyan Ding, Panwen Hu, Jie Li, Rui Huang

cs.CV updates on arXiv.org arxiv.org

arXiv:2403.16888v1 Announce Type: new
Abstract: Semantic Scene Completion (SSC) aims to jointly infer semantics and occupancies of 3D scenes. Truncated Signed Distance Function (TSDF), a 3D encoding of depth, has been a common input for SSC. Furthermore, RGB-TSDF fusion, seems promising since these two modalities provide color and geometry information, respectively. Nevertheless, RGB-TSDF fusion has been considered nontrivial and commonly-used naive addition will result in inconsistent results. We argue that the inconsistency comes from the sparsity of RGB features upon …

3d scenes abstract arxiv consistent cs.cv encoding entropy feature function fusion loss semantic semantics type

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Principal Data Engineering Manager

@ Microsoft | Redmond, Washington, United States

Machine Learning Engineer

@ Apple | San Diego, California, United States