About me

Noah is a Professor of Computer Science at Cornell Tech interested in computer vision and computer graphics, and a member of the Cornell Graphics and Vision Group. He also works at Google DeepMind in NYC. His research interests are in computer vision and graphics, in particular in 3D understanding and depiction of scenes from images. Noah is the recipient of a PECASE, a Microsoft New Faculty Fellowship, an Alfred P. Sloan Fellowship, a SIGGRAPH Significant New Researcher Award, and is a Fellow of the ACM.

For a quick overview of my interests, see my TR35 talk. View my CV.

  Code and Data

Code: My software can be found on my GitHub page, including the bundler structure from motion toolkit and code for image matching using vocabulary trees. Or visit the bundler homepage for more information.

Datasets: Structure-from-Motion and Location Recognition datasets are now centralized on the BigSFM page.

  Publications

See my Google Scholar page.

  Selected Projects

Generative Image Dynamics Generative Image Dynamics
Zhengqi Li, Richard Tucker, Noah Snavely, Aleksander Holynski
CVPR 2024
Best Paper Award
[www, pdf]
Streetscapes Streetscapes
Boyang Deng, Richard Tucker, Zhengqi Li, Leo Guibas, Noah Snavely, Gordon Wetzstein
SIGGRAPH 2024
[www, pdf]
NeRFiller: Completing Scenes via Generative 3D Inpainting NeRFiller
Ethan Weber, A. Holynski, V. Jampani, S. Saxena, N. Snavely, A. Kar, A. Kanazawa
CVPR 2024
[www, pdf, code]
Doppelgangers: Learning to Disambiguate Images of Similar Structures WonderJourney
Koven Yu, Haoyi Duan, Junhwa Hur, Kyle Sargent, Michael Rubinstein, Bill Freeman Forrester Cole, Deqing Sun Noah Snavely, Jiajun Wu, Charles Herrmann
CVPR 2024
[www, pdf, code]
Tracking Everything Everywhere
                        All at Once Tracking Everything Everywhere All at Once
Qianqian Wang, Yen-Yu Chang, Ruojin Cai, Zhengqi Li, Bharath Hariharan, Aleksander Holynski, Noah Snavely
ICCV 2023
Best Student Paper Award
[www, pdf, code]
Doppelgangers: Learning to Disambiguate Images of Similar Structures Doppelgangers
Ruojin Cai, Joseph Tung, Qianqian Wang, Bharath Hariharan, Hadar Averbuch-Elor, Noah Snavely
ICCV 2023
[www, pdf, code]
ASIC: Aligning Sparse in-the-wild
Image Collections ASIC: Aligning Sparse in-the-wild Image Collections
Kamal Gupta, V. Jampani, C. Esteves, A. Shrivastava, A. Makadia, N. Snavely, A. Kar
CVPR 2023
[www, pdf]
FactorMatte: Redefining Video Matting for Re-Composition Tasks FactorMatte
Zeqi Gu, Wenqi Xian, Noah Snavely, Abe Davis
SIGGRAPH 2023
[www, pdf, code]
DynIBaR: Dynamic Neural
                        Image-Based Rendering DynIBaR
Zhengqi Li, Qianqian Wang, Forrester Cole, Richard Tucker, Noah Snavely
CVPR 2023
Best Paper Honorable Mention
[www, pdf, code]
Persistent Nature: A Generative Model of Unbounded 3D Worlds Persistent Nature
Lucy Chai, Richard Tucker, Zhengqi Li, Phillip Isola, Noah Snavely
CVPR 2023
[www, pdf, code]
Neural Scene Chronology Neural Scene Chronology
Haotong Lin, Qianqian Wang, Ruojin Cai, Sida Peng, Hadar Averbuch-Elor, Xiaowei Zhou, Noah Snavely
CVPR 2023
[www, pdf, code]
Neural Lens Modeling Neural Lens Modeling
Wenqi Xian, Aljaž Božič, Noah Snavely, Christoph Lassner
CVPR 2023
[www, pdf, code]
Accidental Light Probes Accidental Light Probes
Koven Yu, Samir Agarwala, Charles Herrmann, Richard Szeliski, Noah Snavely, Jiajun Wu, Deqing Sun
CVPR 2023
[www, pdf]
Omnimatte3D: Associating Objects and their Effects in Unconstrained Monocular Video Omnimatte3D
Mohammed Suhail, Erika Lu, Zhengqi Li, Noah Snavely, Leonid Sigal, Forrester Cole
CVPR 2023
[www, pdf]
Seeing a Rose in 5,000 Ways Seeing a Rose in 5,000 Ways
Yunzhi Zhang, Shangzhe Wu, Noah Snavely, Jiajun Wu
CVPR 2023
[www, pdf]
What's in a Decade? Transforming Faces Through Time What's in a Decade?
Eric Ming Chen, Jin Sun, Apoorv Khandelwal Dani Lischinski, Noah Snavely, Hadar Averbuch-Elor
Eurographics 2023
[www, pdf]
InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images InfiniteNature-Zero
Zhengqi Li, Qianqian Wang, Noah Snavely, Angjoo Kanazawa
ECCV 2022
[www, pdf]
ARF: Artistic Radiance Fields ARF: Artistic Radiance Fields
Kai Zhang, Nick Kolkin, Sai Bi, Fujun Luan, Zexiang Xu, Eli Shechtman, Noah Snavely
ECCV 2022
[www, pdf, code]
Structure and Motion for Casual Videos Structure and Motion for Casual Videos
Zhoutong Zhang, Forrester Cole, Zhengqi Li, Michael Rubinstein, Noah Snavely, Bill Freeman
ECCV 2022
[code, pdf]
Dimensions of Motion Dimensions of Motion
Richard Strong Bowen*, Richard Tucker*, Ramin Zabih, Noah Snavely
3DV 2022
[www, pdf]
Neural 3D Reconstruction in the Wild Neural 3D Reconstruction in the Wild
Jiaming Sun, Xi Chen, Qianqian Wang, Zhengqi Li, Hadar Averbuch-Elor, Xiaowei Zhou, Noah Snavely
SIGGRAPH 2022
[www, pdf]
IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images IRON: Inverse Rendering by Optimizing Neural SDFs and Materials
Kai Zhang, Fujun Luan, Zhengqi Li, Noah Snavely
CVPR 2022
[www, pdf]
Deformable Sprites for Unsupervised Video Decomposition Deformable Sprites for Unsupervised Video Decomposition
V. Ye, Z. Li, R. Tucker, A. Kanazawa, N. Snavely
CVPR 2022
[www, pdf]
3D Moments from Near-Duplicate Photos 3D Moments from Near-Duplicate Photos
Qianqian Wang, Zhengqi Li, David Salesin, Noah Snavely, Brian Curless, Janne Kontkanen
CVPR 2022
[www, pdf]
Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image Infinite Nature
Andrew Liu*, Richard Tucker*, Varun Jampani, Ameesh Makadia, Noah Snavely, Angjoo Kanazawa
ICCV 2021
[www, pdf]
Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision Towers of Babel
Xiaoshi Wu*, Hadar Averbuch-Elor*, Jin Sun, Noah Snavely
ICCV 2021
[www, pdf, data]
Who's Waldo? Linking People Across Text and Images Who's Waldo?
Claire Yuqing Cui*, Apoorv Khandelwal*, Yoav Artzi, Noah Snavely, Hadar Averbuch-Elor
ICCV 2021
[www, pdf]
IBRNet: Learning Multi-View Image-Based Rendering IBRNet: Learning Multi-View Image-Based Rendering
Qianqian Wang, Z. Wang, K. Genova, P. Srinivasan, H. Zhou, J. Barron, R. Martin-Brualla, N. Snavely, T. Funkhouser
CVPR 2021
[www, pdf]
Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes
Zhengqi Li, Simon Niklaus, Noah Snavely, Oliver Wang
CVPR 2021
[www, pdf]
PhySG: Inverse Rendering with
                        Spherical Gaussians for Physics-based Material Editing and Relighting PhySG: Inverse Rendering with Spherical Gaussians
Kai Zhang*, Fujun Luan*, Qianqian Wang, Kavita Bala, Noah Snavely
CVPR 2021
[www, pdf]
De-rendering the World's Revolutionary Artefacts De-rendering the World's Revolutionary Artefacts
Shangzhe Wu, Ameesh Makadia, Jiajun Wu, Noah Snavely, Richard Tucker, Angjoo Kanazawa
CVPR 2021
[www, pdf]
Extreme Rotation Estimation using Dense Correlation Volumes Extreme Rotation Estimation using Dense Correlation Volumes
Ruojin Cai, Bharath Hariharan, Noah Snavely, Hadar Averbuch-Elor
CVPR 2021
[www, pdf]
KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control KeypointDeformer
Tomas Jakab Richard Tucker, Ameesh Makadia, Jiajun Wu, Noah Snavely, Angjoo Kanazawa
CVPR 2021
[www, pdf]
Wide-Baseline Relative Camera Pose Estimation with Directional Learning Wide-Baseline Relative Camera Pose Estimation with Directional Learning
Kefan Chen, Noah Snavely, Ameesh Makadia
CVPR 2021
[www, pdf]
Repopulating Street Scenes Repopulating Street Scenes
Yifan Wang, Andrew Liu, Richard Tucker, Jiajun Wu, Brian Curless, Steve Seitz, Noah Snavely
CVPR 2021
[www, pdf]
An Ethical Highlighter for People-Centric Dataset Creation An Ethical Highlighter for People-Centric Dataset Creation
Margot Hanley, Apoorv Khandelwal, Hadar Averbuch-Elor, N. Snavely, Helen Nissenbaum
NeurIPS 2020 NBIAIR Workshop [pdf]
MetaSDF: Meta-Learning Signed Distance Functions MetaSDF: Meta-Learning Signed Distance Functions
Vincent Sitzmann, Eric Chan, Richard Tucker, Noah Snavely (Google), Gordon Wetzstein
NeurIPS 2020
[www, pdf]
Multi-Plane Program Induction with 3D Box Priors Multi-Plane Program Induction with 3D Box Priors
Li*, Mao*, Zhang, Freeman, Tenenbaum, Snavely, Wu
NeurIPS 2020
[www, pdf]
Crowdsampling the Plenoptic Function Crowdsampling the Plenoptic Function
Zhengqi Li, Wenqi Xian, Abe Davis, Noah Snavely
ECCV 2020
[www, pdf]
Learning Feature Descriptors using Camera Pose Supervision Learning Feature Descriptors using Camera Pose Supervision
Qianqian Wang, Xiaowei Zhou, Bharath Hariharan, N. Snavely
ECCV 2020
[www, pdf]
Learning to Factorize and Relight a City Learning to Factorize and Relight a City
Andrew Liu, Shiry Ginosar, Tinghui Zhou, Alexei A. Efros, Noah Snavely (Google Research)
ECCV 2020
[www, pdf]
Learning Gradient Fields for Shape Generation Learning Gradient Fields for Shape Generation
Ruojin Cai*, Guandao Yang*, Averbuch-Elor, Hao, Belongie, Snavely, Hariharan
ECCV 2020
[www, pdf]
Hidden Footprints: Learning Contextual Walkability from 3D Human Trails Hidden Footprints: Learning Contextual Walkability from 3D Human Trails
Jin Sun, Hadar Averbuch-Elor, Qianqian Wang, Noah Snavely
ECCV 2020
[www, pdf]
Visual Chirality Visual Chirality
Zhiqiu Lin, Jin Sun, Abe Davis, Noah Snavely
CVPR 2020
[www, pdf]
Single-View View Synthesis with Multiplane Images
Richard Tucker, Noah Snavely (Google Research),
CVPR 2020
[www, pdf]
Lighthouse: Predicting Lighting Volumes
for Spatially-Coherent Illumination Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination
Srinivasan*, Mildenhall*, Tancik, Barron, Tucker, Snavely
CVPR 2020
[www, pdf]
DualSDF: Semantic Shape Manipulation using a Two-Level Representation
DualSDF
Zekun Hao, Hadar Averbuch-Elor, Noah Snavely, Serge Belongie
CVPR 2020
[www, pdf]
Depth Sensing Beyond LiDAR Range
Kai Zhang, Jiaxin Xie, Noah Snavely, Qifeng Chen
CVPR 2020
[www, pdf]
Scene Summarization via Motion Normalization Scene Summarization via Motion Normalization
Scott Wehrwein, Kavita Bala, Noah Snavely,
TVCG 2021
[www, pdf]
GeoStyle: Discovering Fashion Trends and Events GeoStyle: Discovering Fashion Trends and Events
U. Mall, K. Matzen, B. Hariharan, N. Snavely, K. Bala
ICCV 2019
[www, pdf]
UprightNet: Geometry-Aware
  Camera Orientation Estimation from Single Images UprightNet
Wenqi Xian*, Zhengqi Li*, Matthew Fisher, J. Eisenmann, Eli Shechtman, Noah Snavely
ICCV 2019
[www, pdf]
Leveraging Vision Reconstruction Pipelines
for Satellite Imagery Leveraging 3D Vision Pipelines for Satellite Imagery
Kai Zhang, Jin Sun, Noah Snavely
ICCV 3DRW Workshop 2019
[www, pdf]
Learning the Depths of Moving People by Watching Frozen People Learning the Depths of Moving People by Watching Frozen People
Z. Li, T. Dekel, F. Cole, R. Tucker, N. Snavely, C. Liu, W.T. Freeman
CVPR 2019 Best Paper Honorable Mention
[www, pdf]
Pushing the Boundaries of View Extrapolation with Multiplane Images Pushing the Boundaries of View Extrapolation
P. Srinivasan, R. Tucker, J. Barron, R. Ramamoorthi, R. Ng, N. Snavely
CVPR 2019
[www, pdf]
Neural Rerendering in the Wild Neural Rerendering in the Wild
M. Meshry, D. Goldman, S. Khamis, H. Hoppe, R. Pandey, N. Snavely, R. Martin-Brualla
CVPR 2019
[www, pdf]
DeepView: View synthesis
              with Learned Gradient Descent DeepView: View synthesis with Learned Gradient Descent
J. Flynn, M. Broxton, P. Debevec, M. DuVall, G. Fyffe, R. Overbeck, N. Snavely (Google AI), R. Tucker
CVPR 2019
[www, pdf, video]
Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
H. Chen, A. Suhr, D. Misra, N. Snavely, Y. Artzi
CVPR 2019
[GitHub, pdf]
Discovery of Latent 3D Keypoints Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
S. Suwajanakorn, N. Snavely (Google AI), J. Tompson, M. Norouzi
NeurIPS 2018
[www, pdf]
CGIntrinsics CGIntrinsics: Better Intrinsic Images through Physically-Based Rendering
Zhengqi Li and Noah Snavely
ECCV 2018
[webpage, pdf]
Layer-structured 3D Scene Inference via View Synthesis Layer-structured 3D Scene Inference
Shubham Tulsiani, Richard Tucker, and Noah Snavely (Google AI)
ECCV 2018
[www, pdf]
Stereo Magnification Stereo Magnification
Tinghui Zhou, Richard Tucker, John Flynn, Graham Fyffe and Noah Snavely (Google AI)
SIGGRAPH 2018
[www, paper]
MegaDepth MegaDepth: Learning Single-View Depth Prediction from Internet Photos
Zhengqi Li and Noah Snavely
CVPR 2018
[www, code, paper, demo]
BigTime BigTime: Learning Intrinsic Images by Watching the World
Zhengqi Li and Noah Snavely
CVPR 2018
[www, code, paper]
StreetStyle StreetStyle
Kevin Matzen, Kavita Bala, and Noah Snavely
Posted to arXiv, 2017
[www, demo, paper]
Unsupervised Learning of Depth and Ego-Motion from Video Unsupervised Depth and Ego-Motion from Video
Tinghui Zhou, Matthew Brown, Noah Snavely (Google AI), and David Lowe
CVPR 2017
[www, pdf]
Shading Annotations in the Wild Shading Annotations in the Wild
Balazs Kovacs, Sean Bell, Noah Snavely, and Kavita Bala
CVPR 2017
[www, pdf]
Deep Feature Interpolation for Image
                             Content Changes Deep Feature Interpolation
Upchurch, Gardner, Bala, Pless, Snavely, and Weinberger
CVPR 2017
[www, pdf]
When is Rotations Averaging Hard? When is Rotations Averaging Hard?
Kyle Wilson, David Bindel, and Noah Snavely
ECCV 2016
[pdf]
DeepStereo: Learning to Predict New
                             Views from the World's Imagery DeepStereo
John Flynn, Ivan Neulander, James Philbin, Noah Snavely (Google)
CVPR 2016
[video, pdf]
Shadow Detection and Sun Direction
                             in Photo Collections Shadow Detection and Sun Direction in Photo Collections
Scott Wehrwein, Kavita Bala, Noah Snavely
3DV 2015
[www, pdf]
BubbLeNet: Foveated imaging for visual discovery BubbLeNets
Kevin Matzen, Noah Snavely
ICCV 2015
[www with data]
Caliber: The General Camera System Calibrator Caliber: The General Camera System Calibrator
Albert Liu, Steve Marschner, Noah Snavely
IJCV 2016
[www with code]
Material Recognition in the Wild Material Recognition in the Wild
Sean Bell, Paul Upchurch, Kavita Bala, Noah Snavely
CVPR 2015
[www (with CNN models and data)]
Outdoor Illumination Models Reasoning about Photos under Outdoor Illumination
Hauagge, Wehrwein, Upchurch, Bala, Snavely
BMVC 2014
[www]
Scene Chronology Scene Chronology
Kevin Matzen, Noah Snavely
ECCV 2014.
Best Paper Award
[pdf, www]
1DSfM 1DSfM
Kyle Wilson, Noah Snavely
ECCV 2014
[pdf, www+data, code]
Intrinsic images in the Wild Intrinsic Images in the Wild
Sean Bell, Kavita Bala, Noah Snavely
SIGGRAPH 2014
[www]
Minimal Scene Descriptions Minimal Scene Descriptions
Song Cao, Noah Snavely
CVPR 2014
[pdf, www]
NYC3DCars NYC3DCars
Kevin Matzen, Noah Snavely
ICCV 2013
[pdf, www+data, label UI code]
Disambiguating SfM Disambiguating SfM
Kyle Wilson, Noah Snavely
ICCV 2013
[pdf, www, code]
OpenSurfaces OpenSurfaces
Sean Bell, Paul Upchurch, Noah Snavely, Kavita Bala
SIGGRAPH 2013
[publication page] [data] [segmentation UI]

Photometric Ambient Occlusion Photometric Ambient Occlusion
Daniel Hauagge, Scott Wehrwein, Kavita Bala, Noah Snavely
CVPR 2013 [www]
Graph-Based Discriminative Learning for Location Recognition Representing Places with Graphs
Song Cao, Noah Snavely
CVPR 2013 [www]
Worldwide Pose Estimation Worldwide Pose Estimation
Yunpeng Li, Noah Snavely, Dan Huttenlocher, Pascal Fua
ECCV 2012 [www]
Mining Structure in Large Image Collections Mining Structure in Large Image Collections
Yin Lou, Noah Snavely, Johannes Gehrke
ECCV 2012 [www]
Learning to Match Images Learning to Match Images
Cao Song, Noah Snavely
ECCV 2012 Workshop on Web-scale Vision and Social Media [www]
Image Matching using Local Symmetry Features Local Symmetry Features
Daniel Hauagge, Noah Snavely
CVPR 2012 [pdf] [www+code]
Image Description with a Goal Image Description with a Goal
Amir Sadovnik, Yi-I Chiu, Noah Snavely, Shimon Edelman, Tsuhan Chen
CVPR 2012 [pdf]
SfM with MRFs: Discrete-Continuous SfM SfM with MRFs
D. Crandall, A. Owens, N. Snavely, D. Huttenlocher
CVPR 2011, Best paper runner-up. [www] [pdf]
dualrough Dual-Scale Surface Appearance
Chun-Po Wang, Noah Snavely, Steve Marschner
SIGGRAPH Asia 2011
Where's Waldo Where's Waldo? Matching People in Crowds
Rahul Garg, Deva Ramanan Steve Seitz, Noah Snavely
CVPR 2011
PhotoCity PhotoCity
K. Tuite, N. Snavely, D-Y. Hsaio, N. Tabing, Z. Popovic
CHI 2011
Location Recognition using
          2D-to-3D Matching Location Recognition using Prioritized 2D-to-3D Feature Matching
Yunpeng Li, Noah Snavely, Dan Huttenlocher
ECCV 2010
Bundle Adjustment in the Large Bundle Adjustment in the Large
S. Agarwal, N. Snavely, S. Seitz, R. Szeliski
ECCV 2010
Building Rome in a Day Building Rome in a Day
Sameer Agarwal, Noah Snavely, Ian Simon, Steve Seitz, Richard Szeliski
ICCV 2009
The Dimensionality of Scene Appearance The Dimensionality of Scene Appearance
Rahul Garg, Hao Du, Steve Seitz, Noah Snavely
ICCV 2009
Finding Paths Through the World's Photos Finding Paths through the World's Photos
Noah Snavely, Rahul Garg, Steve Seitz, Richard Szeliski
SIGGRAPH 2008
Skeletal sets for efficient
                                  structure from motion Skeletal Sets for Efficient SfM
Noah Snavely, Steve Seitz, Richard Szeliski
CVPR 2008
Photo Tourism Photo Tourism
Noah Snavely, Steve Seitz, Richard Szeliski
SIGGRAPH 2006
Scene summarization for online image
                                  collections Scene Summarization for Online Image Collections
Ian Simon, Noah Snavely, and Steven M. Seitz
ICCV 2007
Multi-view stereo for community photo collections Multi-View Stereo for Community Photo Collections
M. Goesele, N. Snavely, B. Curless, S. Seitz, H. Hoppe
ICCV 2007
Stylizing 2.5D video Stylizing 2.5D Video
Noah Snavely, C. Lawrence Zitnick, Sing Bing Kang, Michael Cohen
NPAR 2006
Spacetime Faces Spacetime Faces
Li Zhang, Noah Snavely, Brian Curless, Steve Seitz
SIGGRAPH 2004
SOLAR project Itanium Binary Optimization
with Saumya Debray and Greg Andrews
Visit the SOLAR page at the University of Arizona