Scholar
MA Li
Google Scholar ID: veS098oAAAAJ
Research Scientist @ Netflix’s Scanline VFX Studio
Citations & Impact
Citations
636
H-index
10
i10-index
10
Publications
20
Co-authors
20
list available
Resume
Academic Achievements
- Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset (CVPR, 2025); Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise (CVPR, 2025, Oral); DifFRelight: Diffusion-Based Facial Performance Relighting (Siggraph Asia, 2024); Fisheye-GS: Lightweight and Extensible Gaussian Splatting Module for Fisheye Cameras (ECCVW, 2024); SpecNeRF: Gaussian Directional Encoding for Specular Reflections (CVPR, 2024); 3D Video Loops from Asynchronous Input (CVPR, 2023); Neural Parameterization for Dynamic Human Head Editing (Siggraph Asia, 2022).
Research Experience
- Currently a Research Scientist at Eyeline Labs, working with Paul Debevec; Research Intern at Meta Reality Labs from May to October 2023, managers Michael Zollhoefer and Christian Richardt; Research Intern at Tencent AI Lab under the guidance of Xiaoyu Li from August 2021 to September 2022.
Education
- PhD: Dept. of Computer Science & Engineering, Hong Kong University of Science and Technology (HKUST), advisor Prof. Pedro V. SANDER, and worked closely with Prof. Liao Jing; Bachelor's Degree: EE from Zhejiang University, graduated in 2019.
Background
- Research Interests: Novel View Synthesis, Neural Rendering, Differentiable Rendering, and other graphics-related vision topics. Before diving into neural rendering research, also engaged in some low-level image and video processing tasks, including image/video stitching, inpainting, HDR creation, style transfer, video stabilization, and optical flow estimation.
