An automated black-and-white image colorization model leveraging Transfer Learning with ResNet-18 and the Lab color space to reconstruct semantically coherent colors in grayscale images.

A Deep Learning based Vapoursynth filter for colorizing and restoring old images and video, based on DeOldify, DDColor, ColorMNet and DeepRemaster.

[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders

📚 A collection of Deep Learning based Image Colorization and Video Colorization papers.

Improvement image/video colorization using Zhang et al. algorithm with object-aware processing for custom recolorization, facial feature correction, and color bleeding prevention

Automatically transform grayscale images into color photos using Deep Learning.

Modernized fork of DeOldify - AI-powered colorization for old photos and films. Updated for PyTorch 2.5+, CUDA 12.x, and Intel GPUs

Automatic black and white photo and video colorization using deep learning (Zhang et al. algorithm). Batch processing support with side-by-side comparison view.

This repository demonstrates browser based implementation of DeOldify that colorizes black & white images. It is powered by Onnx and does not require any web servers.

PyTorch U‑Net image colorization (LAB color space) — trained on COCO, includes evaluation (PSNR/SSIM/RMSE/SNR) and a Gradio demo.

[SIGGRAPH 2025] Official code of the paper "Cobra: Efficient Line Art COlorization with BRoAder References". Cobra：利用更广泛参考图实现高效线稿上色

The official implementation of paper "ColorFlow: Retrieval-Augmented Image Sequence Colorization". ColorFlow：基于检索增强的图像序列上色

Hierarchical image colorization model combining a Swin Transformer encoder with an EMA-based VQ-VAE bottleneck and a residual decoder. Learns discrete color representations and produces realistic, perceptually consistent colorizations

Deep learning grayscale (black and white) to color image conversion using U-Net autoencoder architecture in PyTorch. Converts grayscale images to RGB using LAB color space prediction with encoder-decoder neural networks.

AI-driven object-aware image colorization system that restores grayscale images with realistic, context-sensitive color mapping.

This project implements a GAN model for converting grayscale images to color.

UNet model to colorize black & white images

A deep learning project that automatically colorizes anime sketches using a custom U-Net architecture. The model takes grayscale sketches and color scribbles as input to generate fully colorized anime characters.

A PyTorch implementation of a Variational Autoencoder (VAE) with a U-Net architecture, self-attention, and perceptual loss to colorize grayscale images of birds.

A mobile application that colorizes black and white images using AI, consisting of a Flask backend server and a React Native mobile app.