all AI news
LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation
April 8, 2024, 4:44 a.m. | Xuecan Wang, Shibang Xiao, Xiaohui Liang
cs.CV updates on arXiv.org arxiv.org
Abstract: We present a lightweight solution for estimating spatially-coherent indoor lighting from a single RGB image. Previous methods for estimating illumination using volumetric representations have overlooked the sparse distribution of light sources in space, necessitating substantial memory and computational resources for achieving high-quality results. We introduce a unified, voxel octree-based illumination estimation framework to produce 3D spatially-coherent lighting. Additionally, a differentiable voxel octree cone tracing rendering layer is proposed to eliminate regular volumetric representation throughout the …
abstract arxiv computational cs.cv distribution image light lighting memory quality resources results solution space type voxel
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
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
Data Science Analyst
@ Mayo Clinic | AZ, United States
Sr. Data Scientist (Network Engineering)
@ SpaceX | Redmond, WA