Geometry processing and machine learning with functional maps.

PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation

The source code of the paper "RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos"

Graph generative pre-trained transformer

Backing Up Sketchfab

Project website for 3D Bird Reconstruction (ECCV 2020)

A Python library for working with motion data in numpy or PyTorch

Like SMPL but for bugs

Armature Utility Plugin for Blender

A library for machine learning research on motion capture data

Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.

Official implementation of PartSTAD: 2D-to-3D Part Segmentation Task Adaptation (ECCV 2024).

A library for human kinematic motion and numerical optimization solvers to apply human motion

Python module for parsing BVH (Biovision hierarchical data) mocap files

Load SMPL in blender

[CVPR 2024] This repo is official PyTorch implementation of Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Official implementation of the paper "MotionAGFormer: Enhancing 3D Pose Estimation with a Transformer-GCNFormer Network" (WACV 2024).

Official codebase for 3D-LFM paper. Accepted at CVPR, 2024.

The official implementation of the paper "MAS: Multiview Ancestral Sampling for 3D Motion Generation Using 2D Diffusion"

Search and download glb files from objaverse using semantic search

Reasoning 3D Segmentation - "segment anything"/grounding/part seperation in 3D with natural conversations.

A high-throughput and memory-efficient inference and serving engine for LLMs

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

Refine high-quality datasets and visual AI models

Python wrapper for the arXiv API

CVPR 24 paper: Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs

Official implementation of CVPR24 Highlight paper "Open-vocabulary object 6D pose estimation"

[TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.