Computer Vision
Showing 36 of 711 projects
Official ROS2 driver for Basler GigE Vision, USB3 Vision, and blaze 3D cameras, providing access to pylon API functionalities.
Automated UI testing framework for set-top boxes and smart TVs using infrared commands and video analysis.
A Torch7 package providing extended neural network modules, criterions, and utilities for deep learning research.
A simple, flexible, and extensible object-oriented template for PyTorch projects.
A Docker container for face detection using Faster R-CNN deep learning, processing videos and images with bounding box outputs.
A high-performance Common Lisp library for representing and processing 2D pixel-based images with minimal dependencies.
Automatically classifies and labels urban point clouds using data fusion with public datasets and region growing techniques.
Shallow and deep convolutional neural networks for predicting visual saliency in images using a data-driven approach.
Header-only C++ library for loading and writing DNG/TIFF files with support for RAW, lossless JPEG, and ZIP compression.
Integrates Intel OpenVINO with ROS 2 for efficient deep learning inference in computer vision applications on Intel hardware.
A ROS library for robust plane segmentation from LIDAR, depth camera data, and elevation maps using normal-based clustering.
A deep learning model using generative adversarial networks for fast compressed sensing MRI reconstruction.
A Torch-based deep learning project for breaking CAPTCHA systems using CNN and RNN architectures.
A deep learning model for joint perception and motion prediction in autonomous driving using bird's eye view maps.
A distributed video processing platform built on Apache Storm with OpenCV integration for large-scale computer vision pipelines.
A collection of Jupyter notebooks demonstrating TensorFlow Lite model quantization, conversion, and optimization techniques for deep neural networks.
![[Web]](/_next/image?url=https%3A%2F%2Fgithub.com%2Faravindhm.png%3Fsize%3D40&w=96&q=75){kind=small}
MATLAB code for inverting deep neural network representations to visualize and understand learned features from CVPR 2015.
A YOLO-based object detection system specifically trained to identify DJI drones in images and video.
A multi-sensor dataset for autonomous vehicle and robot navigation, featuring synchronized camera, LiDAR, IMU, and GNSS data collected in urban environments.
A lightweight C/C++ library for fast reading and writing of basic multi-frame TIFF files.
A ROS2 node wrapper for the ORB_SLAM2 library, enabling visual SLAM integration in ROS2 systems.
Unofficial JAX/Flax implementations of deep learning research papers for vision transformers and other architectures.
A public dataset of field images with segmentation masks and plant type annotations for computer vision in precision agriculture.
A deep learning approach that unifies global place recognition and local 6DoF pose refinement for robust relocalization in large-scale 3D point clouds.
A curated archive of research papers and resources on generative modeling, covering GANs, image synthesis, 3D generation, and applications.
A deprecated ROS2 wrapper for Intel RealSense depth cameras (D400 series) to stream sensor data as ROS2 topics.
Open-source implementation of the winning solution for the 2018 Data Science Bowl Kaggle competition using PyTorch and U-Net.
A PyTorch implementation of the DeepDream algorithm for generating psychedelic, dream-like images from neural network activations.
A TensorFlow implementation of hierarchical attentive recurrent neural networks for single object tracking in videos.
A synthetic dataset of 2D imagery, 3D point clouds, and 3D vehicle bounding box labels generated using the Grand Theft Auto 5 game engine.
Open-source software for deep learning-based analysis and visualization of whole slide images in digital pathology.
A TensorFlow-based neural network model for generating descriptive captions from images using Flickr30K and MSCOCO datasets.
An open-source system that uses machine learning on drone video to detect standardized ground symbols indicating disaster victims' needs.
Keras implementation of Pix2pix for image-to-image translation using conditional adversarial networks.
State-of-the-art point location and neighbor finding algorithms for region quadtrees, implemented in Go.
A deep learning-based, threshold-agnostic, subpixel-accurate 2D and 3D spot detection method for fluorescence microscopy and spatial transcriptomics.
Related Tags
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.