March 29, 2024, 4:46 a.m. | Zhihao Liang, Qi Zhang, Ying Feng, Ying Shan, Kui Jia

cs.CV updates on arXiv.org arxiv.org

arXiv:2311.16473v3 Announce Type: replace
Abstract: We propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (GS) that leverages forward mapping volume rendering to achieve photorealistic novel view synthesis and relighting results. Unlike previous works that use implicit neural representations and volume rendering (e.g. NeRF), which suffer from low expressive power and high computational complexity, we extend GS, a top-performance representation for novel view synthesis, to estimate scene geometry, surface material, and environment illumination from multi-view images captured …

abstract arxiv cs.cv implicit neural representations inverse rendering low mapping nerf novel photorealistic power rendering results synthesis type view

AI Research Scientist

@ Vara | Berlin, Germany and Remote

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

Data Analyst (Digital Business Analyst)

@ Activate Interactive Pte Ltd | Singapore, Central Singapore, Singapore