| CARVIEW |
Short Bio
My name is Songyin Wu (吴松隐). I am a Ph.D. student at the University of California, Santa Barbara, advised by Prof. Ling-Qi Yan. My research mainly focuses on rendering. I’m especially interested in exploring novel representations for efficient real-time rendering.
Prior to my PhD studies, I earned my bachelor’s degree at Peking University, where I was fortunate to be supervised by Prof. Baoquan Chen.
Interests
- Rendering
- Inverse Graphics
Education
-
Ph.D. Student in Computer Science, 2022 ~ now
University of California, Santa Barbara
-
BSc in Computer Science, 2017 ~ 2021
Turing Class, Peking University
Recent Publications
Monocular Online Reconstruction with Enhanced Detail Preservation
GFFE: G-buffer Free Frame Extrapolation for Low-latency Real-time Rendering
Unified Gaussian Primitives for Scene Representation and Rendering
ExtraSS: A Framework for Joint Spatial Super Sampling and Frame Extrapolation
BSDF Importance Baking: A Lightweight Neural Solution to Importance Sampling General Parametric BSDFs
Projects
Microfacet Material Energy Compensation
We proposed a neural network approach for microfacet material energy compensation. Our method only takes roughness and F0 parameters for GGX model and predicts energy compensated BRDF values. The model is very effective in the inference stage, and can handle isotropic/anisotropic, colored materials.