SAM 3D Objects

Reference PyTorch implementation and models for DINOv3

RigAnything: Template‑Free Autoregressive Rigging for Diverse 3D Assets (SIGGRAPH TOG 2025)

An addon for Blender enabling just-in-time loading and animation of mesh and particle/ point-cloud sequences.

ViPE: Video Pose Engine for Geometric 3D Perception

Character Animation Diffusion with Any Topology

Single Motion Diffusion Model

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Wan: Open and Advanced Large-Scale Video Generative Models

[ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy

Introduction to state-of-the-art simulation methods for rigid bodies, deformable solids and fluids in the area of visual computing

Python bindings for fast_cd

Python package for rendering 3D scenes and animations using blender.

CoTracker is a model for tracking any point (pixel) on a video.

Python script for converting ShaderToy programs to video/image sequences

[ICCV 2025] PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos

Tracking Any Point (TAP)

Generative Models by Stability AI

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

[NeurIPS 2024] Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models

Official inference repo for FLUX.1 models

A diffuser implementation of Zero123. Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV23)

Let us control diffusion models!

A highly efficient implementation of Gaussian Processes in PyTorch

Bayesian optimization in PyTorch

Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization