all AI news
Towards Balanced RGB-TSDF Fusion for Consistent Semantic Scene Completion by 3D RGB Feature Completion and a Classwise Entropy Loss Function
March 26, 2024, 4:48 a.m. | Laiyan Ding, Panwen Hu, Jie Li, Rui Huang
cs.CV updates on arXiv.org arxiv.org
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
More from arxiv.org / cs.CV updates on arXiv.org
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
2 days, 2 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
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