Scholar
Rundi Wu
Google Scholar ID: ulf_Pt0AAAAJ
Google DeepMind
Citations & Impact
Citations
2,573
H-index
14
i10-index
14
Publications
20
Co-authors
15
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- - SIGGRAPH 2025: Spatiotemporally Consistent Indoor Lighting Estimation with Diffusion Priors
- - CVPR 2025 (Oral): CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
- - CVPR 2025: SimVS: Simulating World Inconsistencies for Robust View Synthesis
- - ICLR 2025 (Spotlight): VLMaterial: Procedural Material Generation with Large Vision-Language Models
- - ECCV 2024 (Oral): Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis
- - ECCV 2024 (Oral): PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation
- - CVPR 2024: ReconFusion: 3D Reconstruction with Diffusion Priors
- - ICLR 2024: Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
- - ICCV 2023: Zero-1-to-3: Zero-shot One Image to 3D Object
- - ICML 2023: Implicit Neural Spatial Representations for Time-dependent PDEs
Research Experience
- Internships:
- - Tencent America (Summer 2022)
- - Google Research (Summer 2023)
- - Google DeepMind (Summer 2024)
Education
- Ph.D.: Columbia University, Advisor: Changxi Zheng (2024)
- B.S.: Turing Class, Peking University (2020), worked with Baoquan Chen
Background
- Research Interests: Computer Vision, Graphics
- Field: Application of deep learning in video generation and 3D reconstruction
- Brief: Currently a research scientist at Google DeepMind, focusing on video processing and 3D object generation.
