47,133 repositories indexed
1–24 of 29 · Most stars
CVAT is a leading data annotation platform for image, video, audio, and 3D datasets. It offers open-source, cloud, and enterprise products, as well as labeling services, with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.
Content aware image resize library
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)
OpenMMLab's next-generation platform for general 3D object detection.
Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
Accelerated deep learning R&D
Algorithms for outlier, adversarial and drift detection
Damselfly is a server-based Photograph Management app. The goal of Damselfly is to index an extremely large collection of images, and allow easy search and retrieval of those images, using metadata such as the IPTC keyword tags, as well as the folder and file names. Damselfly includes support for object/face detection.
World's first general purpose 3D object detection codebse.
Profiling / Debugging assist tools for iOS. (Memory Leak, OOM, ANR, Hard Stalling, Network, OpenGL, Time Profile ...)
A collection of computer vision pre-trained models.
😎 Awesome LIDAR list. The list includes LIDAR manufacturers, datasets, point cloud-processing algorithms, point cloud frameworks and simulators.
Dockerized application that resizes and crops images on the fly, delivering optimized images in formats such as AVIF, WebP, MozJPEG, or PNG using ImageMagick, with an efficient caching system.
Self-hosted open-source web gallery to view your photos and videos featuring mobile-friendly, tagging and AI powered image discovery
Super Fast and Accurate 3D Object Detection based on 3D LiDAR Point Clouds (The PyTorch implementation)
Robotics with GPU computing
CubeSLAM: Monocular 3D Object Detection and SLAM
3D Bounding Box Annotation Tool (3D-BAT) Point cloud and Image Labeling
OverlapNet - Loop Closing for 3D LiDAR-based SLAM (chen2020rss)
Official implementation of Joint Monocular 3D Vehicle Detection and Tracking (ICCV 2019)
SA-SSD: Structure Aware Single-stage 3D Object Detection from Point Cloud (CVPR 2020)
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.
Official Code: Implicit 3D Orientation Learning for 6D Object Detection from RGB Images