《统计学习方法》的代码实现

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

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

LAVIS - A One-stop Library for Language-Vision Intelligence

Reference PyTorch implementation and models for DINOv3

Inpaint anything using Segment Anything and inpainting models.

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

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

[ICCV 2019] Monocular depth estimation from a single image

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) fo…

pytorch implementation of openpose including Hand and Body Pose Estimation.

Tracking Any Point (TAP)

Some awesome AI related books and pdfs for learning and downloading, also apply some playground models for learning

EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation

Code repository for Convolutional Pose Machines, CVPR'16

Exercise notebooks for CVND.

Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"

The code for PixelRefer & VideoRefer

Official repo for PAC-Bayes Information Bottleneck. ICLR 2022.

Repository for the Dynamic Vision Sensor 3D Human Pose Dataset (DHP19).

Moving Object Detection in videos using OpenCV for checking the presence of object and track it in the moving video sequence.

In progress deployment of pose estimation.