Noah Snavely's starred repositories
keypoint_deformer
KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control
doppelgangers
Doppelgangers: Learning to Disambiguate Images of Similar Structures
multi-object-segmentation
Code for "Multi-Object Discovery by Low-Dimensional Object Motion"
wikiscenes
Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision. ICCV 2021.
3d-moments
Code for CVPR 2022 paper '3D Moments from Near-Duplicate Photos'
DirectionNet
Wide-Baseline Relative Camera Pose Estimation with Directional Learning (CVPR 2021)
sorderender
[CVPR2021] De-rendering the World's Revolutionary Artefacts
ExtremeRotation_code
Extreme Rotation Estimation using Dense Correlation Volumes
nerfplusplus
improves over nerf in 360 capture of unbounded scenes
mannequinchallenge
Inference code and trained models for "Learning the Depths of Moving People by Watching Frozen People."
lighthouse
code release for CVPR 2020 Paper Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination https://people.eecs.berkeley.edu/~pratul/lighthouse/
google-research
Google Research
stereo-magnification
Code accompanying the SIGGRAPH 2018 paper "Stereo Magnification: Learning View Synthesis using Multiplane Images"
CGIntrinsics
This is the CGIntrinsics implementation described in the paper "CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering, Z. Li and N. Snavely, ECCV 2018".
layered-scene-inference
Code accompanying the paper "Layer-structured 3D Scene Inference via View Synthesis", ECCV 2018