Showing 21-40 of 159 projects
A PyTorch implementation of the DenseNet architecture, a state-of-the-art convolutional neural network.
An open-source autonomous driving framework that focuses on planning-oriented autonomous driving.
Audio-driven human animation framework for realistic talking faces and body motion generation.
A PyTorch implementation of the SuperGlue graph neural network for feature matching and pose estimation.
A collection of tips and templates for writing research papers and theses using LaTeX, a popular typesetting system.
MagicQuill is an intelligent interactive image editing system powered by AI for CVPR'25.
StarGAN v2 is an open-source PyTorch implementation of a powerful generative model for diverse image-to-image translation.
Thin-Plate Spline Motion Model for image animation, face reenactment, and motion transfer
An image inpainting model using deep neural networks and attention mechanisms, useful for vibe coders working on AI-powered applications.
Real-time dynamic scene rendering using 4D Gaussian Splatting
A research project on Fully Convolutional Networks for Semantic Segmentation, a key computer vision technique.
A high-performance library for efficient neural network pruning and compression across LLMs, vision models, and more.
The I-JEPA codebase provides a self-supervised learning architecture for joint image-text embedding.
Official PyTorch implementation of an efficient 3D mesh reconstruction and high-quality rendering technique.
Official implementation of a CVPR2020 paper for video-based 3D human pose and shape estimation.
FoundationPose is a unified 6D pose estimation and tracking framework for novel objects, useful for computer vision applications.
Political activism documentation on Chinese government censorship, human rights, and censorship circumvention techniques.
Pointcept is a codebase for point cloud perception research, featuring the latest works on 3D computer vision.
An open-source library for local feature matching using Transformers, useful for 3D vision and pose estimation tasks.
A real-time dense SLAM system with 3D reconstruction priors, built for computer vision and robotics applications.
Get weekly updates on trending AI coding tools and projects.