Zhen (Colin) Li

Hello, I am Zhen(Colin) Li , an MSc thesis student at the GrUVi Lab of SFU, under the supervision of Prof. Andrea Tagliasacchi. I obtained my bachelor's degree of the dual degree program between Zhejiang University and Simon Fraser University, majoring in computer science.

My research interests lie in 3D computer vision and computer graphics. My current research focuses on robot-based material capture, neural BRDF modeling, and video models for material appearance. Before this, I worked on large-scale scene reconstruction.

colin_li_2-{at}-sfu-[dot]-ca / CV / Google Scholar / OpenReview / Github

Publications

RoboCloth: A Large-Scale Real Cloth Material Dataset for Neural Reflectance Reconstruction
Zhen (Colin) Li*, Haoran Qin*, Francesco Di Sario, Daniel Rebain, Andrea Tagliasacchi
* equal contribution
Paper / Project Page / Code / Dataset

500 real cloth materials captured by two robot arms under flexible, calibrated camera and light configurations. A neural BRDF prior trained on them transfers to unseen capture systems.

3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
Maria Taktasheva, Lily Goli, Alessandro Fiorini, Zhen (Colin) Li, Daniel Rebain, Andrea Tagliasacchi
Neural Information Processing Systems (NeurIPS) 2025
Paper / Code

3D Gaussian Splatting with planar constraints for improved scene reconstruction. Enables high-quality rendering and meshing of 3D scenes.

NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization
Zhen Li, Weiwei Sun, Shrisudhan Govindarajan, Shaobo Xia, Daniel Rebain, Kwang Moo Yi , Andrea Tagliasacchi
3D Vision (3DV) 2025
Paper / Code

A kernel-free neural surface reconstruction method that leverages point cloud serialization for fast neighbor approximation.

Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.