HaineiFRDM: Explore Diffusion to Restore Defects in Fast-Movement Films

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xun, Rongji, Yuan, Junjie, Wang, Zhongjie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918267084341248
author Xun, Rongji
Yuan, Junjie
Wang, Zhongjie
author_facet Xun, Rongji
Yuan, Junjie
Wang, Zhongjie
contents Existing open-source film restoration methods show limited performance compared to commercial methods due to training with low-quality synthetic data and employing noisy optical flows. In addition, high-resolution films have not been explored by the open-source methods.We propose HaineiFRDM(Film Restoration Diffusion Model), a film restoration framework, to explore diffusion model's powerful content-understanding ability to help human expert better restore indistinguishable film defects.Specifically, we employ a patch-wise training and testing strategy to make restoring high-resolution films on one 24GB-VRAMR GPU possible and design a position-aware Global Prompt and Frame Fusion Modules.Also, we introduce a global-local frequency module to reconstruct consistent textures among different patches. Besides, we firstly restore a low-resolution result and use it as global residual to mitigate blocky artifacts caused by patching process.Furthermore, we construct a film restoration dataset that contains restored real-degraded films and realistic synthetic data.Comprehensive experimental results conclusively demonstrate the superiority of our model in defect restoration ability over existing open-source methods. Code and the dataset will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24946
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HaineiFRDM: Explore Diffusion to Restore Defects in Fast-Movement Films
Xun, Rongji
Yuan, Junjie
Wang, Zhongjie
Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
Existing open-source film restoration methods show limited performance compared to commercial methods due to training with low-quality synthetic data and employing noisy optical flows. In addition, high-resolution films have not been explored by the open-source methods.We propose HaineiFRDM(Film Restoration Diffusion Model), a film restoration framework, to explore diffusion model's powerful content-understanding ability to help human expert better restore indistinguishable film defects.Specifically, we employ a patch-wise training and testing strategy to make restoring high-resolution films on one 24GB-VRAMR GPU possible and design a position-aware Global Prompt and Frame Fusion Modules.Also, we introduce a global-local frequency module to reconstruct consistent textures among different patches. Besides, we firstly restore a low-resolution result and use it as global residual to mitigate blocky artifacts caused by patching process.Furthermore, we construct a film restoration dataset that contains restored real-degraded films and realistic synthetic data.Comprehensive experimental results conclusively demonstrate the superiority of our model in defect restoration ability over existing open-source methods. Code and the dataset will be released.
title HaineiFRDM: Explore Diffusion to Restore Defects in Fast-Movement Films
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
url https://arxiv.org/abs/2512.24946