Explore Projects
Discover 159 open source projects
Showing 41-60 of 159 projects
OpenGVLab/InternImage
A PyTorch-based computer vision foundation model with deformable convolutions for object detection and segmentation.
52CV/CVPR-2021-Papers
This repository contains the CVPR 2021 conference papers, which may be of interest to computer vision and AI developers.
NVlabs/FoundationStereo
FoundationStereo is a CVPR 2025 Best Paper Nomination project for zero-shot stereo matching using AI.
swz30/Restormer
Highly efficient transformer-based model for high-resolution image restoration tasks like deblurring, deraining, and denoising.
nbei/Deep-Flow-Guided-Video-Inpainting
A PyTorch implementation of a deep learning-based video inpainting algorithm.
KaiyangZhou/CoOp
A prompt learning framework for vision-language models.
ankush-me/SynthText
Open-source Python library for generating synthetic text images, useful for computer vision tasks.
muskie82/MonoGS
A CVPR'24 highlighted Python library for building Gaussian Splatting SLAM systems for robotics.
hila-chefer/Transformer-Explainability
Official PyTorch implementation for a novel method to visualize classifications by Transformer based networks.
adobe-research/custom-diffusion
Custom Diffusion: A Python implementation of text-to-image diffusion models for computer vision applications.
SizheAn/PanoHead
A Python-based library for 3D full-head synthesis in 360-degree images, focusing on computer vision and AI.
Yuliang-Liu/Monkey
A Python library for working with large multi-modal models, focusing on image resolution and text labeling.
microsoft/Magma
Magma is a foundation model for building multimodal AI agents, enabling next-gen AI applications.
zhoubolei/bolei_awesome_posters
Collection of CVPR and NeurIPS poster examples and templates for AI/ML researchers and developers.
facebookresearch/MetaCLIP
A research project from Facebook that explores multimodal AI models for computer vision and language tasks.
sshaoshuai/PointRCNN
A 3D object proposal generation and detection library from point cloud data, useful for computer vision.
zju3dv/4K4D
This repository provides a real-time 4D view synthesis system that can generate 4K resolution outputs.
gege-circle/.github
A Vue-based chat application with real-time functionality
DepthAnything/Video-Depth-Anything
A PyTorch-based library for consistent depth estimation in super-long videos using transformers.
showlab/ShowUI
Open-source end-to-end vision-language-action model for GUI agents and computer usage analysis.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.