Boost segmentation model mIoU/Dice instantly WITHOUT retraining. A plug-and-play, training-free optimization module. Published in NeurIPS & JMLR. Compatible with SAM, DeepLab, SegFormer, and more. 🧩

LitePT: Lighter Yet Stronger Point Transformer

Everything about the 'Large Scale Vertebrae Segmentation Challenge' @ MICCAI 2019-2020

A computationally efficient and robust LiDAR-inertial odometry (LIO) package

[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

MedDINOv3: How to adapt vision foundation models for medical image segmentation?

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

[ICCV 2021] A dataset of non-rigidly deforming objects.

Offical Implementation of SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations

Depth Anything 3

Official Implementation of Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

A novel segmentation model termed Swin UNEt TRansformers (Swin UNETR). Specially for the task of 3D semantic segmentation.

Pytorch framework for doing deep learning on point clouds.

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

InteriorGS: 3D Gaussian Splatting Dataset of Semantically Labeled Indoor Scenes

Repository of the paper "AnyUp: Universal Feature Upsampling".

Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.

Official implementation of AppAgentX: Evolving GUI Agents as Proficient Smartphone Users

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

NEO Series: Native Vision-Language Models from First Principles

Official Repository of STS Challenges 😎

Fifth solution for tooth segmentation

Python implementation of "Efficient Graph-Based Image Segmentation" paper

A no dependency, header-only, fast supervoxel segmentation library for 3D point clouds

💫 Industrial-strength Natural Language Processing (NLP) in Python

Open-Set Grounded Text-to-Image Generation

Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series