Noah Snavely

ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild CVPR 2026 Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly CVPR 2026 Long-Tail Internet Photo Reconstruction CVPR 2026 ORBIT: Benchmarking SfM in the Wild with 360deg Video CVPR 2026 ShadowDraw: From Any Object to Shadow-Drawing Compositional Art CVPR 2026 ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training CVPR 2026 Beyond the Frame: Generating 360deg Panoramic Videos from Perspective Videos ICCV 2025 Can Generative Video Models Help Pose Estimation? CVPR 2025 Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features CVPR 2025 FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution ICCV 2025 Generating 3D-Consistent Videos from Unposed Internet Photos CVPR 2025 LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias ICLR 2025 MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos CVPR 2025 MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps ICCV 2025 Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos CVPR 2025 Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images ICCV 2025 Generative Image Dynamics CVPR 2024 MegaScenes: Scene-Level View Synthesis at Scale ECCV 2024 NeRFiller: Completing Scenes via Generative 3D Inpainting CVPR 2024 Neural Gaffer: Relighting Any Object via Diffusion NeurIPS 2024 Physics-Based Interaction with 3D Objects via Video Generation ECCV 2024 WonderJourney: Going from Anywhere to Everywhere CVPR 2024 Accidental Light Probes CVPR 2023 ASIC: Aligning Sparse in-the-wild Image Collections ICCV 2023 Doppelgangers: Learning to Disambiguate Images of Similar Structures ICCV 2023 DynIBaR: Neural Dynamic Image-Based Rendering CVPR 2023 Neural Lens Modeling CVPR 2023 Neural Scene Chronology CVPR 2023 Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular Video CVPR 2023 Persistent Nature: A Generative Model of Unbounded 3D Worlds CVPR 2023 Seeing a Rose in Five Thousand Ways CVPR 2023 Tracking Everything Everywhere All at Once ICCV 2023 3D Moments From Near-Duplicate Photos CVPR 2022 ARF: Artistic Radiance Fields ECCV 2022 Deformable Sprites for Unsupervised Video Decomposition CVPR 2022 InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images ECCV 2022 IRON: Inverse Rendering by Optimizing Neural SDFs and Materials From Photometric Images CVPR 2022 Structure and Motion from Casual Videos ECCV 2022 Unsupervised Semantic Segmentation by Distilling Feature Correspondences ICLR 2022 De-Rendering the World's Revolutionary Artefacts CVPR 2021 Extreme Rotation Estimation Using Dense Correlation Volumes CVPR 2021 IBRNet: Learning Multi-View Image-Based Rendering CVPR 2021 Infinite Nature: Perpetual View Generation of Natural Scenes From a Single Image ICCV 2021 KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control CVPR 2021 Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes CVPR 2021 PhySG: Inverse Rendering With Spherical Gaussians for Physics-Based Material Editing and Relighting CVPR 2021 Repopulating Street Scenes CVPR 2021 Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision ICCV 2021 Who's Waldo? Linking People Across Text and Images ICCV 2021 Wide-Baseline Relative Camera Pose Estimation With Directional Learning CVPR 2021 An Analysis of SVD for Deep Rotation Estimation NeurIPS 2020 Crowdsampling the Plenoptic Function ECCV 2020 Depth Sensing Beyond LiDAR Range CVPR 2020 DualSDF: Semantic Shape Manipulation Using a Two-Level Representation CVPR 2020 Hidden Footprints: Learning Contextual Walkability from 3D Human Trails ECCV 2020 Learning Feature Descriptors using Camera Pose Supervision ECCV 2020 Learning Gradient Fields for Shape Generation ECCV 2020 Learning to Factorize and Relight a City ECCV 2020 Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination CVPR 2020 MetaSDF: Meta-Learning Signed Distance Functions NeurIPS 2020 Multi-Plane Program Induction with 3D Box Priors NeurIPS 2020 Single-View View Synthesis With Multiplane Images CVPR 2020 Visual Chirality CVPR 2020 DeepView: View Synthesis With Learned Gradient Descent CVPR 2019 GeoStyle: Discovering Fashion Trends and Events ICCV 2019 Learning the Depths of Moving People by Watching Frozen People CVPR 2019 Neural Rerendering in the Wild CVPR 2019 Pushing the Boundaries of View Extrapolation With Multiplane Images CVPR 2019 TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments CVPR 2019 UprightNet: Geometry-Aware Camera Orientation Estimation From Single Images ICCV 2019 CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering ECCV 2018 Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning NeurIPS 2018 Layer-structured 3D Scene Inference via View Synthesis ECCV 2018 Learning Intrinsic Image Decomposition From Watching the World CVPR 2018 MegaDepth: Learning Single-View Depth Prediction From Internet Photos CVPR 2018 Deep Feature Interpolation for Image Content Changes CVPR 2017 Shading Annotations in the Wild CVPR 2017 Unsupervised Learning of Depth and Ego-Motion From Video CVPR 2017 DeepStereo: Learning to Predict New Views From the World's Imagery CVPR 2016 BubbLeNet: Foveated Imaging for Visual Discovery ICCV 2015 Material Recognition in the Wild With the Materials in Context Database CVPR 2015 Minimal Scene Descriptions from Structure from Motion Models CVPR 2014 Graph-Based Discriminative Learning for Location Recognition CVPR 2013 Network Principles for SfM: Disambiguating Repeated Structures with Local Context ICCV 2013 NYC3DCars: A Dataset of 3D Vehicles in Geographic Context ICCV 2013 Photometric Ambient Occlusion CVPR 2013