Showing 81-100 of 159 projects
PyTorch implementation of a multi-label image recognition model using graph convolutional networks.
An official implementation of HigherHRNet, a scale-aware human pose estimation model.
DEIM: A real-time object detection system using DETR with improved matching for fast convergence.
A temporal-consistent diffusion model for real-world video super-resolution and deflickering.
This repository contains the official implementation of the MobileCLIP and MobileCLIP2 research papers, focused on AI-powered mobile app development.
BASNet is a PyTorch library for boundary-aware salient object detection, useful for computer vision applications.
A deep learning-based object detection library written in C++, with a focus on single-shot refinement for accurate object detection.
A curation of the latest CVPR (Computer Vision and Pattern Recognition) papers, code, and demos for AI-powered developers.
Mip-Splatting is a novel 3D Gaussian splatting algorithm for alias-free novel view synthesis.
A framework for training and deploying latent diffusion models for image reconstruction and generation.
Code for the Lovรกsz-Softmax loss, a loss function for image segmentation using neural networks.
A C++ library for fast and controllable 3D editing using Gaussian splatting, presented at CVPR 2024.
An image super-resolution library that uses diffusion inversion to enable arbitrary-steps upscaling.
An AI-powered tool for generating highly dynamic and realistic portrait image animations from video inputs.
An open-source, state-of-the-art image restoration library for deblurring, denoising, and deraining tasks.
PoolFormer is a vision transformer model that achieves state-of-the-art performance on image classification tasks.
An open-source library for learning continuous image representation using local implicit image function.
PhysGaussian is a physics-integrated 3D Gaussian generative dynamics library for CVPR 2024.
Official implementation of X-Decoder, a generalized decoding model for pixel, image, and language tasks.
Official codebase for OMG-LLaVA and OMG-Seg, state-of-the-art computer vision models presented at CVPR-24 and NeurIPS-24.
Get weekly updates on trending AI coding tools and projects.