#
Highlights
- Pro
Starred repositories
Toolkits for the synthetic multiview cattle 3D detection and action recognition dataset, MultiviewC.
Segment Anything in High Quality [NeurIPS 2023]
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Awesome multilingual OCR and Document Parsing toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools,…
[ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
An open source implementation of CLIP.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)
Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Simple Online Realtime Tracking with a Deep Association Metric
Simple, online, and realtime tracking of multiple objects in a video sequence.
DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding
freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Python and OpenCV based object tracking software
A curated list of awesome data labeling tools
Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO