3 papers
cs.CV2024
PRTGaussian: Efficient Relighting Using 3D Gaussians with Precomputed Radiance Transfer
Libo Zhang, Yuxuan Han, Wenbin Lin +2
We present PRTGaussian, a realtime relightable novel-view synthesis method made possible by combining 3D Gaussians and Precomputed Radiance Transfer (PRT). By fitting relightable G…
cs.CV2024
NeRF as a Non-Distant Environment Emitter in Physics-based Inverse Rendering
Jingwang Ling, Ruihan Yu, Feng Xu +2
Physics-based inverse rendering enables joint optimization of shape, material, and lighting based on captured 2D images. To ensure accurate reconstruction, using a light model that…
cs.CV2022
Structure-aware Editable Morphable Model for 3D Facial Detail Animation and Manipulation
Jingwang Ling, Zhibo Wang, Ming Lu +3
Morphable models are essential for the statistical modeling of 3D faces. Previous works on morphable models mostly focus on large-scale facial geometry but ignore facial details. T…