Scholar
Kai Zhang
Google Scholar ID: eVv0MrsAAAAJ
Research Scientist, Adobe Research
Citations & Impact
Citations
4,323
H-index
20
i10-index
23
Publications
20
Co-authors
66
list available
Contact
Publications
Resume (English only)
Academic Achievements
- PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction, ICLR 2024 (Spotlight)
- DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model, ICLR 2024 (Spotlight)
- Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model, ICLR 2024
- LRM: Large Reconstruction Model for Single Image to 3D, ICLR 2024 (Oral)
- Ray Conditioning: Trading Photo-Consistency for Photo-realism in Multi-view Image Generation, ICCV 2023
- ARF: Artistic Radiance Fields, ECCV 2022
- IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images, CVPR 2022 (Oral)
Research Experience
- Currently a Research Scientist at Adobe Research, focusing on 3D reconstruction and generation as well as inverse graphics problems.
Education
- Received a bachelor's degree from Tsinghua University in 2017 and a PhD from Cornell University in 2022, where he worked under Prof. Noah Snavely.
Background
- Research interests include 3D reconstruction and generation, inverse graphics problems. The latest active research area is generative 3D reconstructor that can 1) reconstruct from sparse posed/unposed images; 2) hallucinate the unseen regions; 3) be generalizable; 4) be robust to imperfect inputs, including lighting variations, motion blur, etc.; 5) work on both object-level and scene-level.
