Universal 3D World Reconstruction with Any-Prior Prompting

Code for "FlashWorld: High-quality 3D Scene Generation within Seconds"

Awesome lists about framework figures in papers

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

Reference PyTorch implementation and models for DINOv3

A unified inference and post-training framework for accelerated video generation.

Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.

Cameras as Relative Positional Encoding

[Siggraph Asia 2025] Official code release of our paper "Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxy"

Official repository for "SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE"

Multi-Joint dynamics with Contact. A general purpose physics simulator.

JavaScript Gaussian Splatting library.

Unified framework for robot learning built on NVIDIA Isaac Sim

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.

[CVPR2025] Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion

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

[CVPR 2025 Highlight] Material Anything: Generating Materials for Any 3D Object via Diffusion

[CVPR'25] Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System

🧡 Follow everything in one place

Blender Python scripts for rendering images directly from command-line interface

PyTorch native quantization and sparsity for training and inference

Pythonic tool for orchestrating machine-learning/high performance/quantum-computing workflows in heterogeneous compute environments.

Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation

[ICLR 2025] Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

[CVPR 2025 Highlight] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

Python package to corrupt arbitrary images.