Official implementation of Video-DPM

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

SHIFT Dataset DevKit - CVPR2022

Toolkit for JRDB dataset

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

Code for the ShapeR research paper

The official implementation of the paper “VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction.”

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

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video

[NeurIPS 2025] Pixel-Perfect Depth

Dynamic 3D Foundation Model using Causal Transformer

[CVPR 2025] Prompt Depth Anything

AnyDepth: Depth Estimation Made Easy

Atom3d, atomising geometry, is a mesh processing toolbox specifically designed for 3D learning.

[ASPLOS 2026] CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting with CPU Offloading

SID2026

The official implementation of InfiniteVGGT

[NeurIPS 2025] LabelAny3D: Label Any Object 3D in the Wild

Code for "InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields"

Python wrapper for the NVIDIA cuSFM library

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

Official implementation of "AirSim360: A Panoramic Simulation Platform within Drone View"

Official implementation of "DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training".

Official implementation of "Depth Anything in 360°: Towards Scale Invariance in the Wild".

Visual Geometry Transformer for Autonomous Driving

Official implementation of DA²: Depth Anything in Any Direction

Official implementation of "Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation".