DexMV: Imitation Learning for Dexterous Manipulation from Human Videos, ECCV 2022

MANO hand model in PyTorch (anatomy consistent, anchors, etc)

SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

HaMeR: Reconstructing Hands in 3D with Transformers

Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset

oCaption: Leveraging OpenAI's GPT-4 Vision for Advanced Image Captioning

Automatically exported from code.google.com/p/v-hacd

⭐️ Companies that don't have a broken hiring process

An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.

A unified framework for robot learning

Repository to accompany RSS 2018 paper on dexterous hand manipulation

Simple NodeJs Web-based User Study Interface for Researchers

This is the official implementation of our paper "Hypergraph Transformer for Skeleton-based Action Recognition."

A toolbox for skeleton-based action recognition.

A Simple Baseline for Human Motion Prediction

Official Reimplementation of Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips (DiffHOI, ICCV23) https://judyye.github.io/diffhoi-www/

TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement, ECCV'22

team Doggeee's solution to Ego4D LTA challenge@CVPRW23'

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

Cache PyTorch module outputs on-the-fly

Dataset and code for the paper "First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations", CVPR 2018.

Official implementation of "SViT: Revisiting Token Pruning for Object Detection and Instance Segmentation"

Source code for the GCPR 2022 paper: <InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction>

Official implementation for the CVPR'23 paper: Visibility Aware Human-Object Interaction Tracking from Single RGB Camera

[CVPR 2023] MOVES: Manipulated Objects in Video Enable Segmentation

Code for recreating the HoS benchmark of VISOR

Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".