Scholar
Zhihao (Zach) Xia
Google Scholar ID: Rc4ZMCEAAAAJ
Phota Labs, ex-Adobe
Citations & Impact
Citations
673
H-index
13
i10-index
15
Publications
20
Co-authors
23
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- 1. Instruction-based Image Manipulation by Watching How Things Move (CVPR 2025)
- 2. LEDiff: Latent Exposure Diffusion for HDR Generation (CVPR 2025)
- 3. Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable (CVPR 2025)
- 4. Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos (ACM ToG 2025)
- 5. Explorative Inbetweening of Time and Space (ECCV 2024)
- 6. Restoration by Generation with Constrained Priors (CVPR 2024)
- 7. Self-Supervised Burst Super-Resolution (ICCV 2023)
- 8. DiffusionRig: Learning Personalized Priors for Facial Appearance Editing (CVPR 2023)
- 9. Semi-supervised Parametric Real-world Image Harmonization (CVPR 2023)
- 10. Neural Photo-Finishing (SIGGRAPH Asia 2022)
Research Experience
- Worked at research labs at Google Research, Adobe Research, NUS, and KAUST.
Education
- PhD from Washington University (WashU), advised by Ayan Chakrabarti; Bachelor's degree from School of the Gifted Young at USTC
Background
- Research interests: photography, video, and generative AI. Was a research scientist and tech lead on Marc Levoy's team at Adobe, where he built AI features for photographers (e.g., Adobe Adaptive Profile, AI denoising). Also launched Project Indigo, a camera app leveraging computational photography.
Miscellany
- Personal interests: Hiring people interested in GenAI, photography, or building visual products.
