real time face swap and one-click video deepfake with only a single image

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

AI agents running research on single-GPU nanochat training automatically

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"

A modular graph-based Retrieval-Augmented Generation (RAG) system

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

DeepFaceLab is the leading software for creating deepfakes.

Mamba SSM architecture

A collaboration friendly studio for NeRFs

🔎 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting

Closed-form Continuous-time Neural Networks

Source code for the CVPR'20 paper "Blindly Assess Image Quality in the Wild Guided by A Self-Adaptive Hyper Network"

[CVPRW oral 2022] MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment

[CVPR'20] Official SPAQ & Implementation

[WACV 2024 Oral] - ARNIQA: Learning Distortion Manifold for Image Quality Assessment

Official implementation for "Image Quality Assessment using Contrastive Learning"

Official implementation for CVPR2023 Paper "Re-IQA : Unsupervised Learning for Image Quality Assessment in the Wild"

[ Official ] - PIPAL Dataset and Training Codebase. ECCV-2020, NTIRE-21/22.

Unfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolution

Forward-Only Zeroth-Order Prompt Optimization for Test-Time Adaptation (CVPR 2026)