Track when a car driver turns head and closes eyes via an optical camera

Toolbox for manipulating image annotations in computer vision

Find strongest response of convolutional layers on an image dataset. Automatically compute receptive field for any CNN layer.

A web page for MiikeMineStamps dataset

Software to render 3D CAD models on custom background using Blender

Parameter-Efficient Long-Tailed Recognition

This repository is based on Ultralytics/yolov5, with adjustments to enable polygon prediction boxes.

Affine matching C++ library for OpenCV (based on ASIFT)

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Pytorch framework for doing deep learning on point clouds.

Keras implementation of RetinaNet object detection.

An extension of Open3D to address 3D Machine Learning tasks

Telenav.AI competition public repository

Frustum PointNets for 3D Object Detection from RGB-D Data

StyleGAN - Official TensorFlow Implementation

No description provided.

Analyze traffic given a set of optical cameras in urban areas

Datasets, Transforms and Models specific to Computer Vision

Spherical CNNs

YOLOv2 in PyTorch

No description provided.

Face recognition using Tensorflow

TensorFlow Implementation of "Unsupervised Cross-Domain Image Generation"

A Tensorflow Implementation of Faster RCNN

Tensorflow implementation of "Learning Deconvolution Network for Semantic Segmentation"

An Implementation of Fully Convolutional Networks in Tensorflow.

Is a fork of RCNN, which is tuned to generate selective search proposals in the format I need

Put a few canonical images onto different backgrounds to create a variety of training images

combine several repos

No description provided.