Lists (32)
2D / 3D Keypoints
3D-Avatar-NonParam
3D from Image/Video
3D from Text
3D + Language
Architecture
Curation List
Datasets
Depth Estimation
Digital Human <-> Robotics
Hand Mesh Recovery
HSI-Generation
Human Body Mesh
Human Motion
Human-Object-Interaction
Human-Object-Reconstruction-3D
Human Parsing
Human-Scene-Interaction
Image Generation
Inpainting / EditAnything
Large Scale Foundation Model
Misc
NeRF / SDF / Implicit
Object-6DOF
Object Detection
Object Tracking
Pose Embedding
Segmentation
Tools
Video + Language
Vision Embedding
Vision + Language
Stars
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
[SIGGRAPH ASIA 2025] Code for PartUV: Part-Based UV Unwrapping of 3D Meshes
Kandinsky 5.0: A family of diffusion models for Video & Image generation
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…
Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton…
WebGL point cloud viewer for large datasets
TAPIP3D: Tracking Any Point in Persistent 3D Geometry
Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
A paper list for spatial reasoning
FlowFeat: Pixel-Dense Embedding of Motion Profiles (NeurIPS 2025 Spotlight)
Official Implementation of Human Motion Synthesis in 3D Scenes via Unified Scene Semantic Occupancy (AAAI2026)
[NeurIPS 2025] Tracking and Understanding Object Transformations
SnapMoGen: Human Motion Generation from Expressive Texts [NeurIPS 2025]
This is an implementation of zero-shot instance segmentation using Segment Anything.
Anny, A Free and Interpretable Human Body Model for all ages, written in PyTorch.
[ICCV'25] Method for generating static human-object interactions
Krea Realtime 14B. An open-source realtime AI video model.
A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.
Code for "PHUMA: Physically-Grounded Humanoid Locomotion Dataset"
Stable Video Diffusion Training Code and Extensions.
VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos
Fast and Universal 3D reconstruction model for versatile tasks
[ICCV 2025] SuperDec: 3D Scene Decomposition with Superquadric Primitives.