"MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation"

Official Implementation of Particulate: Feed-Forward 3D Object Articulation

Part-X-MLLM: Part-aware 3D Multimodal Large Language Model

Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

Build Native Cross-platform apps and web-apps in dart with native performance

Open source C++ physics engine library in 3D

[NeurIPS 2025] LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans

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

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

The Wasm Shell

WebGPU cross-platform app with CMake/Emscripten

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model

Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features

[ICCV 2025 Highlight] DIMO: Diverse 3D Motion Generation for Arbitrary Objects

[PG2025] PaMO: Parallel Mesh Optimization for Intersection-Free Low-Poly Modeling on the GPU

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

An unofficial and simplified implementation of SIGGRAPH 2025 best paper nominate: CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image, working in progress

[SIGGRAPH Asia 2025 - TOG] Official implementation of MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

Liquid templating library for dart

🔥🔥🔥 Set the world of 3D faces on fire with INFERNO 🔥🔥🔥

[SIGGRAPH 2025] PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer

[AAAI 2025] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

A project to fine-tune a DINO vision model for 3D-aware tasks

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

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

LL3M writes Python code that generates 3D assets in Blender.