Explore Projects
Discover 848 open source projects
Showing 701-720 of 848 projects
gokayfem/awesome-vlm-architectures
A curated list of famous vision-language models and their architectures for developers working with AI tools.
yitu-opensource/T2T-ViT
A Tokens-to-Token Vision Transformer (T2T-ViT) model for training Vision Transformers from scratch on ImageNet.
ucbdrive/few-shot-object-detection
A PyTorch implementation of few-shot object detection benchmarks for AI and computer vision researchers.
HyperGAN/HyperGAN
A composable GAN framework with API and user interface for building generative AI models.
farzaa/DeepLeague
An open-source computer vision and deep learning library for analyzing League of Legends gameplay.
lightaime/deep_gcns_torch
A PyTorch library for Deep Graph Convolutional Networks (DeepGCNs) and other graph neural network models.
whai362/PSENet
Official PyTorch implementation of the PSENet text detection algorithm for computer vision tasks.
roatienza/Deep-Learning-Experiments
A collection of deep learning experiments and tutorials to help developers understand and apply deep learning techniques.
facebookarchive/C3D
C3D is a modified version of BVLC caffe to support 3D ConvNets for computer vision applications.
Kagami/go-face
A face recognition library for Go that uses the dlib computer vision library.
NVlabs/VoxFormer
Official PyTorch implementation of VoxFormer, a state-of-the-art 3D computer vision model for autonomous driving and scene understanding.
cpvrlab/ImagePlay
ImagePlay is a rapid prototyping application for image processing, targeting developers working with computer vision and AI.
RedApparat/FaceDetector
A Java library for face detection on Android devices, useful for building computer vision apps.
aitorzip/DeepGTAV
A C++ plugin that transforms Grand Theft Auto V into a self-driving car research environment
AravisProject/aravis
A vision library for genicam-based cameras, enabling developers to build vision-based applications.
SHI-Labs/Neighborhood-Attention-Transformer
A transformer-based model for neighborhood attention, useful for computer vision tasks.
FoundationVision/GLEE
A general object foundation model for computer vision tasks in images and videos at scale
facebookresearch/ToMe
A method to increase the speed and lower the memory footprint of existing vision transformers.
VITA-Group/DeblurGANv2
DeblurGAN-v2 is a deep learning-based solution for fast and high-quality image deblurring, useful for vibe coders working with computer vision.
lessthanoptimal/BoofCV
A fast computer vision library for 3D reconstruction, calibration, tracking, and more, written in Java.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.