Presentation
DE-NeRF: DEcoupled Neural Radiance Fields for View-consistent Appearance Editing and High-frequency Environmental Relighting
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.
Event Type
Technical Paper
TimeThursday, 10 August 202311:37am - 11:47am PDT
LocationRoom 502 AB
Research & Education
Livestreamed
Recorded
Artificial Intelligence/Machine Learning
Rendering
Video
FC
FCS
V
VS
EFC