Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

The state-of-the-art image restoration model without nonlinear activation functions.

AI powered speech denoising and enhancement

General Speech Restoration

ECCV2020 - Practical Deep Raw Image Denoising on Mobile Devices

Emote Portrait Alive - using ai to reverse engineer code from white paper. (abandoned)

A simple Python wrapper for audio noise reduction RNNoise. Simplifies work with it, adds new trained models and detailed instructions for training.

NBNet: Noise Basis Learning for Image Denoising with Subspace Projection

2D AI-NR model for raw images, including dataset、training、infer.

Deep learning based denoiser for Cycles, Blender's physically-based production renderer.

SpeechDenoiser: Real-Time Speech Denoising with ONNX Welcome to SpeechDenoiser, a simple and effective solution for real-time speech denoising using an ONNX model. This repository contains everything you need to get started with enhancing audio quality by reducing noise, making it perfect for improving voice recordings and live communication.

[NeurIPS`25] TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer

A curated list of awesome 3D point cloud denoising papers

Python implementation of OMLSA+IMCRA algorithm for speech enhancement.

Calligraphic Images Denoising by GAN

图像增强与去噪

A Real-ESRGAN model trained on a custom dataset

Single Channel Speech Enhancement Methods and Toolbox

A generic denoising method for 1D spectra based on singular value decomposition

Augmentations for Neural Networks. Implementation of Torchvision's transforms using OpenCV and additional augmentations for super-resolution, restoration and image to image translation.