PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data

We present SceneFactor, a diffusion-based approach for large-scale 3D scene generation that enables controllable generation and effortless editing.

Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations

Official code for VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator

A library for fast ray intersection on triangle meshes for python based on BVH

Official repository for BrickGPT, the first approach for generating physically stable toy brick models from text prompts.

A curated list of awesome 3D point cloud denoising papers

Laplacian filtering in the context of mesh denoising

Code implementation of the paper "World-in-World: World Models in a Closed-Loop World"

Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views

A Survey of Reinforcement Learning for Large Reasoning Models

ICCV 25 ModSkill: Physical Character Skill Modularization

Official PyTorch Implementation of "Latent Diffusion Model Without Variational Autoencoder".

a unified reinforcement learning toolbox for joint RL on language models and diffusion models

[NeurIPS 2025] GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer

Dynamics for retopology.

A collection of noise designs for diffusion models [Eurographics Tutorial / SIGGRAPH Course, 2025]

An end-to-end text-to-mesh FLUX.1 Kontext [dev]-based diffusion model specialized on texture generation

Neural Visibility of Point Sets [SIGGRAPH Asia 2025]

[SIGGRAPH Asia 2025] Official implementation of Surface-Aware Distilled 3D Semantic Features

Official repository for "PoissonNet: A Local-Global Approach for Learning on Surfaces"

Official repository for the article Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models (https://arxiv.org/abs/2507.12318)

dInfer: An Efficient Inference Framework for Diffusion Language Models

Official code for paper "InstantSfM: Fully Sparse and Parallel Structure-from-Motion"

[ACL 2025] Cautious Next Token Prediction

The official implementation of 'SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation', SIGGRAPH Asia 2025