6 papers
Diffusion-Based Material Regularization for Physics-Based Inverse Rendering
Jingwang Ling, Lifan Wu, Feng Xu +1
Reconstructing physics-based 3D assets -- geometry, materials, and illumination -- from multi-view images is a core problem in computer graphics and vision, and a prerequisite for…
Guiding-Based Importance Sampling for Walk on Stars
Tianyu Huang, Jingwang Ling, Shuang Zhao +1
Walk on stars (WoSt) has shown its power in being applied to Monte Carlo methods for solving partial differential equations, but the sampling techniques in WoSt are not satisfactor…
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…
2DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Features
Ruihan Yu, Tianyu Huang, Jingwang Ling +1
2D Gaussian Splatting has recently emerged as a significant method in 3D reconstruction, enabling novel view synthesis and geometry reconstruction simultaneously. While the well-kn…
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…
High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Rendering
Xin Ming, Jiawei Li, Jingwang Ling +2
Readily editable mesh blendshapes have been widely used in animation pipelines, while recent advancements in neural geometry and appearance representations have enabled high-qualit…