Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Detection, segmentation, tracking, OCR models, 3D reconstruction and classical vision.
Signals: computer-vision, object-detection, image-segmentation, yolo, opencv, image-classification, pose-estimation, object-tracking
1,474 results
Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series
Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.
[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale
Two-stage CenterNet
StarDist - Object Detection with Star-convex Shapes
The PyTorch Implementation based on YOLOv4 of the paper: "Complex-YOLO: Real-time 3D Object Detection on Point Clouds"
PANet for Instance Segmentation and Object Detection
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
Single-Shot Refinement Neural Network for Object Detection, CVPR, 2018
Yolov5 deepsort inference，使用YOLOv5+Deepsort实现车辆行人追踪和计数，代码封装成一个Detector类，更容易嵌入到自己的项目中
[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions
[CVPR2026] Detect Anything via Next Point Prediction
[CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"
动态语义SLAM 目标检测+VSLAM+光流/多视角几何动态物体检测+octomap地图+目标数据库
[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence
🕶 A curated list of Tiny Object Detection papers and related resources.
在 oxford hand 数据集上对 YOLOv3 做模型剪枝（network slimming）
SECOND for KITTI/NuScenes object detection
Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.
fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing data operation costs, all with unmatched scalability.
Codes for our paper "CenterNet: Keypoint Triplets for Object Detection" .
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
You Only Look Once for Panopitic Driving Perception.（MIR2022）
[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy
24,545 repositories in the index in total.
