Showing 1–20 of 20 results
/ Date/ Name
Mar 16, 2017Convolutional neural network architecture for geometric matchingAug 13, 2019Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual LocalizationOct 24, 2018Neighbourhood Consensus NetworksMar 21, 2023Real-time volumetric rendering of dynamic humansApr 22, 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse ConvolutionsMay 9, 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local FeaturesMay 18, 2022BodyMap: Learning Full-Body Dense Correspondence MapDec 19, 2017End-to-end weakly-supervised semantic alignmentJul 14, 2023CoTracker: It is Better to Track TogetherJul 8, 2024TAPVid-3D: A Benchmark for Tracking Any Point in 3DDec 9, 2025Efficiently Reconstructing Dynamic Scenes One D4RT at a TimeSep 9, 2021Reconstructing and grounding narrated instructional videos in 3DFeb 1, 2024BootsTAP: Bootstrapped Training for Tracking-Any-PointMay 3, 2023DynamicStereo: Consistent Dynamic Depth from Stereo VideosApr 30, 2025Direct Motion Models for Assessing Generated VideosDec 19, 2024Scaling 4D RepresentationsNov 7, 2022Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable CategoriesDec 6, 2022Self-Supervised Correspondence Estimation via Multiview RegistrationJul 22, 2023Replay: Multi-modal Multi-view Acted Videos for Casual HolographyApr 8, 2025TAPNext: Tracking Any Point (TAP) as Next Token Prediction