My name is Songyin Wu(吴松隐). Currently I’m a student in UCSB, supervised by Prof. Lingqi Yan. My research mainly focuses on rendering. Besides the research, I’m a big fan of video games(Apex Legends, Tom Clancy’s Rainbow Six Siege, etc) and tennis.
Prior to UCSB, I spent about 1 year in the Innovation Engineering Group of Microsoft Research Asia as a research assistant with Jongyoo Kim.
BSc in Computer Science, 2017 ~ 2021
Turing Class, Peking University
Computer Science, 2022 ~ now
University of California, Santa Barbara
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.
We proposed a decouple pipeline, using a neural network as a coordinate-independent feature extractor and a light-weight decision tree as a coordinate-dependent regressor, to relocate camera 6D pose by a RGB image. Our approach can be adapted in a new scene with only few-shot data while achieving reasonable relocalization accuracy.