HaineiFRDM: Explore Diffusion to Restore Defects in Fast-Movement Films
This work addresses film restoration for high-resolution, fast-movement films, offering an open-source alternative to commercial methods, though it appears incremental by building on diffusion models.
The paper tackles the problem of restoring defects in fast-movement films, where existing open-source methods underperform due to low-quality synthetic data and noisy optical flows, and proposes HaineiFRDM, a diffusion-based framework that achieves superior defect restoration ability over existing open-source methods, as demonstrated by comprehensive experimental results.
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.