Computer Vision
Showing 36 of 711 projects
A lightweight neural network for near-real-time semantic segmentation of LiDAR point clouds using polar coordinate quantization.
A curated list of deep learning research papers and implementations for high dynamic range image and video synthesis.
A MATLAB/Octave toolbox for processing High Dynamic Range (HDR) images, including tone mapping and expansion operators.
A cross-platform image viewer for inspecting and rendering raw pixel data from Luminance, YUV, RGB, ARGB, and Bayer formats.
A vision transformer-based deep learning model for automated instance segmentation and classification of cell nuclei in histopathology images.
A graphical application for rapidly prototyping and deploying computer vision algorithms, primarily for robotics.
A neural network playground built in pure Swift for iOS, with no third-party dependencies.
A Python toolbox for image segmentation featuring superpixel segmentation, object center detection, and region growing with shape priors.
A neural networks toolbox for medical image analysis, providing specialized layers, models, and utilities for TensorFlow/Keras.
A re-implementation of the SPP-net object detection algorithm using spatial pyramid pooling in deep convolutional networks for visual recognition.
A real-time RGB-based pipeline for object detection and 6D pose estimation using a denoising autoencoder trained on simulated 3D views.
A curated list of deep learning resources for 3D shape processing, covering classification, reconstruction, and generation.
TensorFlow implementation of weakly-supervised object localization using only image-level labels, without bounding box annotations.
A C++/TensorRT inference module for RangeNet++, enabling fast LiDAR semantic segmentation for robotics applications.
A fast, cross-platform image decoding library with clean APIs for C, C++, and Python, supporting 20+ formats.
A command-line utility that uses convolutional neural networks to search and filter videos based on objects and places that appear in them.
A ROS 2 node for detecting AprilTag fiducial markers in camera images and publishing their poses and metadata.
A simple, multi-language implementation of the Iterative Closest Point algorithm for 3D point cloud registration.
A full LiDAR SLAM system for static environment mapping using LiDAR with optional GPS, IMU, and odometry support.
An optimized, lightweight CUDA-based 3D reconstruction implementation derived from the original Kinfu algorithm.
A minimal implementation of Deep Convolutional Generative Adversarial Networks (DCGAN) using TensorLayerX for generating realistic images.
A Rust library for calculating perceptual hash values of images using multiple algorithms.
A JAX library implementing Lie groups for rigid body transformations in computer vision and robotics.
A Python toolbox for content-aware restoration of fluorescence microscopy images using deep learning.
ROS 2 wrapper for Stereolabs ZED cameras, providing access to depth, point clouds, object detection, and spatial mapping.
A Docker-based image annotation tool for bounding box labeling with auto-labeling support, designed for deep learning training.
A curated list of top-tier publications and resources for LiDAR-Visual fusion SLAM systems.
A Swift library for detecting and cropping faces, barcodes, and text in images using iOS 11 Vision API.
A centralized Python framework for agricultural machine learning, providing access to public datasets, benchmarks, pretrained models, and synthetic data generation.
A TensorFlow-based object detection model that localizes and identifies multiple objects in images using SSD MobileNet V1 or Faster R-CNN ResNet101.
A convolutional neural network for CAPTCHA recognition using Keras and PyTorch.
A ROS stack providing perception packages for 2D image and 3D point cloud processing in robotics.
A PyTorch Vision-like library for downloading, manipulating, and loading event-based/spike-based neuromorphic datasets.
An integrated framework for training custom generative AI image-to-image models using GANs, Diffusion, and Consistency Models.
A deep learning-based solution for automatically recognizing and solving 12306 railway website captchas.
A real-time fiducial tag system for LiDAR point clouds, robust to lighting and compatible with visual markers like AprilTags.
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.