Alternatives and similar repositories for JOSH

Users that are interested in JOSH are comparing it to the libraries listed below

• hongsukchoi / HSfM_RELEASE
  Code release for paper "Reconstructing People, Places, and Cameras", In CVPR 2025 (Highlight)
  ☆144Updated last month
• fanegg / Human3R
  An unified model for 4D human-scene reconstruction
  ☆421Updated this week
• jiyewise / MocapEvery
  Author's implementation of the paper Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera (C…
  ☆68Updated last year
• moonbow721 / DPoser-X
  [ICCV 2025 Oral] DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior
  ☆200Updated 2 months ago
• saidwivedi / InteractVLM
  [CVPR 2025] InteractVLM: 3D Interaction Reasoning from 2D Foundational Models
  ☆120Updated 3 weeks ago
• xiexh20 / HDM
  Official implementation for Hierarachical Diffusion Model in CVPR24 Template free reconstruction of human object interaction
  ☆92Updated 9 months ago
• SMPLCap / WHAC
  [ECCV 2024] Official Code for "WHAC: World-grounded Humans and Cameras"
  ☆134Updated 2 months ago
• eth-ait / Gaussian-Garments
  Code for paper "Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photo-Realistic Appearance from Multi-View Video"
  ☆158Updated 6 months ago
• ChiSu001 / SAT-HMR
  [CVPR 2025] SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens
  ☆98Updated 4 months ago
• boqian-li / ETCH
  [ICCV 2025 Highlight] ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness
  ☆119Updated 3 months ago
• 3DAnimals / 3DAnimals
  3DAnimals: A machine learning framework for reconstructing articulated 3D animals from images
  ☆125Updated 2 months ago
• zju3dv / text_scene_motion
  [CVPR 2024] Generating Human Motion in 3D Scenes from Text Descriptions
  ☆100Updated last year
• Coral79 / Unimotion
  Pytorch implementation of Unimotion: Unifying 3D Human Motion Synthesis and Understanding.
  ☆83Updated 8 months ago
• isarandi / smplfitter
  The Fast Way From Vertices to Parametric 3D Humans
  ☆151Updated 2 months ago
• eth-ait / ReLoo
  ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild (ECCV2024)
  ☆62Updated 2 months ago
• sha2nkt / deco
  Estimate vertex-level 3D human-scene and human-object contacts across the full body mesh
  ☆80Updated 10 months ago
• snuvclab / gtu
  [CVPR 2024] Official Repo of Guess The Unseen (GTU)
  ☆69Updated 4 months ago
• YuxuanSnow / Phy-SIC
  [SIGGGRAPHASIA2025] PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image
  ☆42Updated last month
• amundra15 / livehand
  Official PyTorch implementation of the ICCV '23 paper LiveHand
  ☆70Updated last year
• facebookresearch / nymeria_dataset
  Nymeria: a massive collection of multimodal egocentric daily motion in the wild
  ☆142Updated 4 months ago
• alparius / pico
  [CVPR 2025] PICO: Reconstructing 3D People In Contact with Objects
  ☆52Updated 3 months ago
• ligengen / EgoGen
  [CVPR 2024] Official code for EgoGen: An Egocentric Synthetic Data Generator
  ☆87Updated 7 months ago
• lijiaman / chois_release
  Official Implementation of the Paper: Controllable Human-Object Interaction Synthesis (ECCV 2024 Oral)
  ☆136Updated 11 months ago
• riccardomarin / NICP
  ☆46Updated last year
• zju3dv / RelightableAvatar
  [CVPR 2024 (Highlight)] Relightable and Animatable Neural Avatar from Sparse-View Video
  ☆135Updated last year
• zju3dv / Motion-2-to-3
  Code for "Motion-2-to-3: Leveraging 2D Motion Data to Boost 3D Motion Generation", Arxiv 2024
  ☆102Updated last month
• facebookresearch / AnimalAvatar
  Code from the ECCV 2024 paper "Animal Avatar Reconstructing Animatable 3D Animals from Casual Videos".
  ☆78Updated 2 months ago
• eth-ait / AvatarPose
  Official Code Release for ECCV 2024 paper AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view …
  ☆40Updated last year
• ChaoyueSong / REACTO
  [CVPR 2024] REACTO: Reconstructing Articulated Objects from a Single Video
  ☆63Updated last year
• lxxue / HSR
  HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos (ECCV 2024)
  ☆33Updated 9 months ago