Code Release of MVInverse: Feedforward Multi-view Inverse Rendering in Seconds

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

Cuda mesh utils.

3D generation made easy!

SAM 3D Objects

[3DV 2026 Oral] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

Depth Anything 3

Official Torch/CUDA Implementation of Faithful Contouring

[NeurIPS 2025] Pixel-Perfect Depth

A simple state update rule to enhance length generalization for CUT3R

Code for "Steerable Scene Generation with Post Training and Inference-Time Search", CoRL 2025

A minimal implementation of DeepMind's Genie world model

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

Code for Faster VGGT with Block-Sparse Global Attention

Sim-to-real and CDM inference code for ManipAsInSim project.

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

[3DV 2026] FastMesh: Efficient Artistic Mesh Generation via Component Decoupling

Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion (ICCV 2025 Highlight)

[CORL 2025 Oral]One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation.

Cameras as Relative Positional Encoding

Official Implementation of "Dens3R: A Foundation Model for 3D Geometry Prediction"

[ICCV 2025] InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes

Code release for paper "Test-Time Training Done Right"

[ICCV 2025] Deeply Supervised Flow-Based Generative Models

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

[ICCV 2025] LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion

Code for "Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations"