Neural MotifsCode for Neural Motifs: Scene Graph Parsing with Global Context (CVPR 2018)
AravisA vision library for genicam based cameras
R2cRecognition to Cognition Networks (code for the model in "From Recognition to Cognition: Visual Commonsense Reasoning", CVPR 2019)
Home PlatformHoME: a Household Multimodal Environment is a platform for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context.
GripProgram for rapidly developing computer vision applications
Imagedetect✂️ Detect and crop faces, barcodes and texts in image with iOS 11 Vision api.
Apc Vision ToolboxMIT-Princeton Vision Toolbox for the Amazon Picking Challenge 2016 - RGB-D ConvNet-based object segmentation and 6D object pose estimation.
Dest🐼 One Millisecond Deformable Shape Tracking Library (DEST)
DirtDIRT: a fast differentiable renderer for TensorFlow
Facesvisiondemo👀 iOS11 demo application for age and gender classification of facial images.
LogGaborA python implementation for a LogGabor filtering and pyramid representation
pulse2perceptA Python-based simulation framework for bionic vision
RecogcisFace detection & recognition AR app using the mlmodel to recognize company employees.
VisionLab📺 A framework with common source code for demo projects that use Vision Framework
sim2real-docsSynthesize image datasets of documents in natural scenes with Python+Blender3D
craft-text-detectorPackaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector
sp segmenterSuperpixel-based semantic segmentation, with object pose estimation and tracking. Provided as a ROS package.
PSCognitiveServicePowershell module to access Microsoft Azure Machine learning RESTful API's or Microsoft cognitive services
ImageCropper✂️ Detect and crop faces, barcodes, texts or rectangle in image with iOS 11 Vision (iOS 10 Core Image) api.(图片裁剪:支持人脸、二维码/条形码、文本、方框)
CPPE-DatasetCode for our paper CPPE - 5 (Medical Personal Protective Equipment), a new challenging object detection dataset
e-verestEVEREST: e-Versatile Research Stick for peoples
HRFormerThis is an official implementation of our NeurIPS 2021 paper "HRFormer: High-Resolution Transformer for Dense Prediction".
TextDetectThis app detects the text from the picture input using camera or photos gallery. The app uses MLVisionTextModel for on device detection. The Vision framework from MLKit of Google is used here.
vision-mlA R-CNN machine learning model for handling Pop-up window in mobile Apps.
halonet-pytorchImplementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones
Vision CoreML-AppThis app predicts the age of a person from the picture input using camera or photos gallery. The app uses Core ML framework of iOS for the predictions. The Vision library of CoreML is used here. The trained model fed to the system is AgeNet.
FNet-pytorchUnofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms
UAV-Stereo-VisionA program for controlling a micro-UAV for obstacle detection and collision avoidance using disparity mapping
iOS14-ResourcesA curated collection of iOS 14 projects ranging from SwiftUI to ML, AR etc.
TinyCogSmall Robot, Toy Robot platform
fuse-med-mlA python framework accelerating ML based discovery in the medical field by encouraging code reuse. Batteries included :)
VidSitu[CVPR21] Visual Semantic Role Labeling for Video Understanding (https://arxiv.org/abs/2104.00990)
flutter-visioniOS and Android app built with Flutter and Firebase. Includes Firebase ML Vision, Firestore, and Storage
VisionComputer Vision And Neural Network with Xamarin
non-contact-sleep-apnea-detectionGihan Jayatilaka, Harshana Weligampola, Suren Sritharan, Pankayaraj Pathmanathan, Roshan Ragel and Isuru Nawinne, "Non-contact Infant Sleep Apnea Detection," 2019 14th Conference on Industrial and Information Systems (ICIIS), Kandy, Sri Lanka, 2019, pp. 260-265, doi: 10.1109/ICIIS47346.2019.9063269.
DonkeyDriftOpen-source self-driving car based on DonkeyCar and programmable chassis
FaceDataA macOS app to parse face landmarks from a video for GANs training
mediapipe plusThe purpose of this project is to apply mediapipe to more AI chips.
SAPC-APCAAPCA (Accessible Perceptual Contrast Algorithm) is a new method for predicting contrast for use in emerging web standards (WCAG 3) for determining readability contrast. APCA is derived form the SAPC (S-LUV Advanced Predictive Color) which is an accessibility-oriented color appearance model designed for self-illuminated displays.
calvinCALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks