The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

PyTorch code and models for the DINOv2 self-supervised learning method.

Code release for NeRF (Neural Radiance Fields)

Reference PyTorch implementation and models for DINOv3

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

CoTracker is a model for tracking any point (pixel) on a video.

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Efficient neural feature detector and descriptor

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)

assistant tools for attention visualization in deep learning

[CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

项目注释+论文复现+算法竞赛+Pytorch实践+LeetCode+VLM预训练

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers. (ICCV 2021 Oral)

🐙 OctoPack: Instruction Tuning Code Large Language Models

DefSLAM: Tracking and Mapping of Deforming Scenes from Monocular Sequences. J.Lamarca, S. Parashar, A. Bartoli & J.M.M. Montiel

WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes