Adaptation of the super resolution SOTA for Art Restoration in camera capture images

TL;DR

This paper adapts a state-of-the-art diffusion model for super-resolution to the task of art restoration, enabling automated enhancement of degraded artworks across various deterioration types with a single fine-tuned model.

Contribution

It introduces a unified diffusion-based super-resolution approach specifically fine-tuned for diverse art restoration tasks, reducing the need for multiple specialized models.

Findings

Effective restoration across multiple degradation types

Single model handles diverse deterioration without multiple fine-tunings

Improved visual quality of degraded artworks

Abstract

Preserving cultural heritage is of paramount importance. In the domain of art restoration, developing a computer vision model capable of effectively restoring deteriorated images of art pieces was difficult, but now we have a good computer vision state-of-art. Traditional restoration methods are often time-consuming and require extensive expertise. The aim of this work is to design an automated solution based on computer vision models that can enhance and reconstruct degraded artworks, improving their visual quality while preserving their original characteristics and artifacts. The model should handle a diverse range of deterioration types, including but not limited to noise, blur, scratches, fading, and other common forms of degradation. We adapt the current state-of-art for the image super-resolution based on the Diffusion Model (DM) and fine-tune it for Image art restoration. Our results show that instead of fine-tunning multiple different models for different kinds of degradation, fine-tuning one super-resolution. We train it on multiple datasets to make it robust. code link: https://github.com/Naagar/art_restoration_DM