A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation

BANMo Building Animatable 3D Neural Models from Many Casual Videos

A Unified Framework for Surface Reconstruction

🎠 MagicPony: Learning Articulated 3D Animals in the Wild (CVPR 2023)

A unified framework for 3D content generation.

Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction. NeurIPS 2021.

Code for "LASR: Learning Articulated Shape Reconstruction from a Monocular Video". CVPR 2021.

SAOR: Single-View Articulated Object Reconstruction, CVPR 2024

Official Implementation of paper "Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence"

A framework for 4D reconstruction from monocular videos.

Code for MagicPose4D: Crafting Articulated Models with Appearance and Motion Control

Project repo for Learning Category-Specific Mesh Reconstruction from Image Collections

A PyTorch Library for Accelerating 3D Deep Learning Research

[SIGGRAPH 2022] ARTEMIS, a novel neural modeling and rendering pipeline for generating ARTiculated neural pets with appEarance and Motion synthesIS.

Awesome papers for markerless animal motion capture and 3D reconstruction.

GART: Gaussian Articulated Template Models

Basics of 2D and 3D Human Pose Estimation.

[ECCV 2024] Official implementation of the paper "X-Pose: Detecting Any Keypoints"

Code for paper ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop.

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

12k labelled instances of dogs in-the-wild with 2D keypoint and segmentations. Dataset released with our ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximizati…

Benchmark Animal Dataset of Joint Annotations (BADJA) with example code, as introduced in "Creatures Great and SMAL: Recovering the shape and motion of animals from video" (ACCV 2018).

This repository contains an implementation for performing 3D animal (quadruped) reconstruction from a monocular image or video. The system adapts the pose (limb positions) and shape (animal type/he…