Scholar
Deqing Sun
Google Scholar ID: t4rgICIAAAAJ
Research Scientist, Google DeepMind
Computer Vision
Optical Flow
Machine Learning
Image Processing
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
17,504
H-index
49
i10-index
76
Publications
20
Co-authors
51
list available
Contact
Email
deqing.sun@gmail.com
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
12 items
LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
2026
Cited
0
UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images
2026
Cited
0
GeCo: A Differentiable Geometric Consistency Metric for Video Generation
2025
Cited
0
EA3D: Online Open-World 3D Object Extraction from Streaming Videos
2025
Cited
0
DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes
2025
Cited
0
Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals
2025
Cited
0
Unified Autoregressive Visual Generation and Understanding with Continuous Tokens
2025
Cited
0
Motion Prompting: Controlling Video Generation with Motion Trajectories
arXiv.org · 2024
Cited
13
Load more
Resume (English only)
Academic Achievements
- Published multiple papers at CVPR 2024 including but not limited to:
- ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image
- DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes
- Telling left from right: Identifying geometry-aware semantic correspondence
- SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild
- Probing the 3d awareness of visual foundation models
- Wonderjourney: Going from anywhere to everywhere
- One-Shot Open Affordance Learning with Foundation Models
- SMooDi: Stylized Motion Diffusion Model
- ContactArt: Learning 3d interaction priors for category-level articulated object and hand poses estimation
- Lumiere: A space-time diffusion model for video generation (SIGGRAPH Asia 2024)
- Gala3d: Towards text-to-3d complex scene generation via layout-guided generative gaussian splatting (ICML 2024)
- Hoi-diff: Text-driven synthesis of 3d human-object interactions using diffusion models (ICLR 2024)
Research Experience
- Program Chair for ICCV 2025
- Guest editor for TPAMI special issue on Generative AI in 3D Vision
- Area Chairs for ECCV (2018, 2022, 2024), ICLR 2024, NeurIPS 2023, ICCV 2023, CVPR (2019, 2020, 2022, 2023), BMVC (2019, 2020)
- Co-organized Workshop/Tutorial on AI for Content Creation at SIGGRAPH 2018 and CVPR 2019-2023
- Co-organized Workshop on What is Motion for? at ECCV 2022
- Co-organized Workshop on What is Optical Flow for? at ECCV 2018
- Guest editor for CVIU special issue on Deep Learning for Image Restoration
- Reviewer for National Science Foundation (NSF)
Background
Senior Staff Research Scientist at Google.
Co-authors
51 total
Ming-Hsuan Yang
University of California at Merced; Google DeepMind
Varun Jampani
Vice President of Research, Stability AI
Jan Kautz
Vice President of Research, NVIDIA Research
Michael J. Black
Max Planck Institute for Intelligent Systems
Charles Herrmann
Cornell University
Ming-Yu Liu
Vice President of Research at NVIDIA, IEEE Fellow
Hanspeter Pfister
An Wang Professor of Computer Science, Harvard University
Jinshan Pan
Nanjing University of Science and Technology
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up