Depth Anything 3

Reference PyTorch implementation and models for DINOv3

CUDA accelerated rasterization of gaussian splatting

Python composable command line interface toolkit

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia, Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

The official repository of [CVPR2025] PerLA: Perceptive 3D Language Assistant

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

[3DV 2025] Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model

[ICCV 2025] PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes

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

😎 up-to-date & curated list of awesome 3D Visual Grounding papers, methods & resources.

HoloPart: Generative 3D Part Amodal Segmentation

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

[NeurIPS 2024] Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding

Minimal reproduction of DeepSeek R1-Zero

Reasoning 3D Segmentation - "segment anything"/grounding/part seperation in 3D with natural conversations.

SAMPart3D: Segment Any Part in 3D Objects

Solve puzzles. Learn CUDA.

[ICML 2024] LEO: An Embodied Generalist Agent in 3D World

Collection of Summer 2026 tech internships!

CUDA accelerated rasterization of gaussian splatting

[ICLR 2025] Duoduo CLIP: Efficient 3D Understanding with Multi-View Images

🕷️ SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency

Master programming by recreating your favorite technologies from scratch.

Animation engine for explanatory math videos

Render COLMAP reconstructed Model with Pytorch3D

Official implementation for "DMesh: A Differentiable Representation for General Meshes" (NeurIPS 2024)

[CVPR '24] Official repository of the paper "Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected Features".