Scholar
Zhixin Shu
Google Scholar ID: gp6HUP0AAAAJ
Adobe Research
Citations & Impact
Citations
2,763
H-index
21
i10-index
30
Publications
20
Co-authors
0
Contact
Publications
Resume
Academic Achievements
- FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads, ICCV 2025
- Augmented Mass-Spring Model for Real-Time Dense Hair Simulation, ICCV 2025
- GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR, ICCV 2025
- SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces, CVPR 2025
- Free-viewpoint Human Animation with Pose-correlated Reference Selection, CVPR 2025
- MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data, CVPR 2025
- Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization, CVPR 2025
- Perm: A Parametric Representation for Multi-Style 3D Hair Modeling, ICLR 2025 (spotlight)
- Rig3DGS: Creating Controllable Portraits from Casual Monocular Videos, 3DV 2025
- Generative Portrait Shadow Removal, SIGGRAPH Asia 2024 (TOG)
- COMPOSE: Comprehensive Portrait Shadow Editing, ECCV 2024
- LRM-Zero: Training Large Reconstruction Models with Synthesized Data, NeurIPS 2024
- Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning, CVPR 2024
- In-N-Out: Face Video Inversion and Editing with Volumetric Decomposition, CVPR 2024
Research Experience
- Serving as a research scientist at Adobe Research, working on multiple research projects.
Education
- Ph.D. in Computer Science from Stony Brook University in 2019.
Background
- Currently a research scientist at Adobe Research since 2020. Research interests lie at the intersection of computer vision, computer graphics, and machine learning, with a focus on human-related controllable generation, 3D modeling, reconstruction, relighting, and editing.