Overall framework
Abstract
V-RGBX is an intrinsic-aware video editing framework that combines video inverse rendering, photorealistic video synthesis from intrinsic channels, and keyframe-based editing. Its interleaved conditioning mechanism supports physically grounded edits to intrinsic properties such as albedo, normal, material, and irradiance.
Type
Publication
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Tong WU 吴桐
Assistant Professor @ Fudan
My research interests include 3d vision, long-tailed recognition, and robustness.