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
Variants of Vision Transformer and its downstream tasks
Official PyTorch Implementation of Hypercorrelation Squeeze for Few-Shot Segmentation, ICCV 2021
Implementation of Multi-State Constraint Kalman Filter (MSCKF) for Vision-aided Inertial Navigation. This is my master's thesis.
[CoRL2022] CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
Dataset, code and model for the CVPR'20 paper "The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction". And for the ECCV'20 SimAug paper.
AI-powered padel analytics
[EMNLP2024 Demo], [ICASSP 2025], [ICASSP 2026] A user-friendly library for reproducible video moment retrieval and highlight detection. It also supports audio moment retrieval.
javascript access webcam stream and take photo
A fast Python implementation of Seam Carving for Content-Aware Image Resizing.
Official code for "A Normalized Gaussian Wasserstein Distance for Tiny Object Detection"
The Go-To Choice for CV Data Visualization, Annotation, and Model Analysis.
Some simple computer vision implementations using OpenCV
Deformable Style Transfer (ECCV 2020)
A curated list of awesome resources for adversarial examples in deep learning
Official Code of Paper "Reversible Column Networks" "RevColv2"
A curated list of dedicated resources and applications
Fast and memory-efficient clustering
[CVPR 2025] Source codes for the paper "3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning"
We evaluate our method on different datasets (including ShapeNet, CUB-200-2011, and Pascal3D+) and achieve state-of-the-art results, outperforming all the other supervised and unsupervised methods and 3D representations, all in terms of performance, accuracy, and training time.
Simba is a program used to repeat certain (complicated) tasks. Typically these tasks involve using the mouse and keyboard. Simba is programmable, which means you can design your own logic and steps that Simba will follow, based upon certain input such as colors on the screen.
[ICCV '21] In this repository you find the code to our paper "Keypoint Communities".
webcamGPT - chat with video stream 💬 + 📸
Multi-View Mesh Reconstruction with Neural Deferred Shading (CVPR 2022)
24,544 repositories in the index in total.
