Presentation / Installation


DE-NeRF: DEcoupled Neural Radiance Fields for View-consistent Appearance Editing and High-frequency Environmental Relighting
SessionEnvironment Rendering: NeRFs on Earth
DescriptionWe propose DE-NeRF, a novel neural radiance field editing method that decouples geometry, appearance, and lighting from the input scene by optimizing the learnable features on a mesh proxy and its lighting representation consisting of an environment map and lighting network. It achieves view-consistent editing and high-frequency environmental relighting.
Authors
Tong Wu
Institute of Computing Technology, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Jia-Mu Sun
Institute of Computing Technology, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Yu-Kun Lai
Cardiff University
Lin Gao
Institute of Computing Technology, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Event Type
Technical Paper
TimeThursday, 10 August 202311:37am - 11:47am PDT
LocationRoom 502 AB
ACM Digital Library Technical Paper PDF
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Thursday, 10 August 202310:45am - 12:15pm PDTRoom 502 AB
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Artificial Intelligence/Machine Learning
Rendering
Video
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
Environment Rendering: NeRFs on Earth - Q&A and Interactive Discussion