Noah Snavely

Google (United States) — United States

Computer Science · Physical Sciences

64h-index27.7kcitations235works4.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(147), Computer Graphics and Visualization Techniques(70), Advanced Image and Video Retrieval Techniques(67), Robotics and Sensor-Based Localization(54), Advanced Image Processing Techniques(32)

Publications235 total

ShadowDraw: From Any Object to Shadow-Drawing Compositional Art
arXiv (Cornell University)·2025Open Access
Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features
2025· 1 cited
MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
2025· 9 cited
Can Generative Video Models Help Pose Estimation?
2025· 1 cited
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
2025
Generating 3D-Consistent Videos from Unposed Internet Photos
2025
Eye2Eye: A Simple Approach for Monocular-to-Stereo Video Synthesis
arXiv (Cornell University)·2025Open Access
FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution
arXiv (Cornell University)·2025Open Access
ObjectCarver: Semi-Automatic Segmentation, Reconstruction and Separation of 3D Objects
2025
Can Generative Video Models Help Pose Estimation?
arXiv (Cornell University)·2024Open Access
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
arXiv (Cornell University)·2024Open Access
Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features
arXiv (Cornell University)·2024Open Access
MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
arXiv (Cornell University)·2024Open Access
Generating 3D-Consistent Videos from Unposed Internet Photos
arXiv (Cornell University)·2024Open Access
MegaScenes: Scene-Level View Synthesis at Scale
Lecture notes in computer science·2024· 5 cited
LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias
arXiv (Cornell University)·2024Open Access
PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation
Lecture notes in computer science·2024· 16 cited
ObjectCarver: Semi-automatic segmentation, reconstruction and separation of 3D objects
arXiv (Cornell University)·2024Open Access
Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion
arXiv (Cornell University)·2024Open Access
Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion
2024· 7 cited
page 1 of 12Next →

Frequent Co-authors

Steven M. Seitz(15), Richard Szeliski(10), Zhengqi Li(6), Richard Tucker(6), Tinghui Zhou(4), Sameer Agarwal(4), Ian Simon(4), Brian Curless(4), John P. Flynn(4), Graham Fyffe(3), Jonathan T. Barron(3), Sean Bell(3), Kavita Bala(3), Bharath Hariharan(3), Matthew Brown(2), David Lowe(2), Michael Goesele(2), Hugues Hoppe(2), Qianqian Wang(2), Pratul P. Srinivasan(2)