针对快速运动与多样缺陷，实现高分辨率结构保真修复。
HaineiFRDM: Structure-Preserving Diffusion for Film Restoration under Fast Motion and Diverse Defects
- 用扩散模型分块建模并融合全局位置信息，保持结构一致。
- 在24GB显存单卡上完成高分辨率修复，减少内存占用。
- 专为电影修复构建数据集，支持真实退化模拟与评估。
现有电影修复方法在快速运动下常出现肢体消失和结构扭曲，源于运动建模不准；同时，对空间持续性与混合缺陷的高分辨率修复研究不足。本文提出HaineiFRDM，一种基于扩散模型的电影修复框架，利用其内容建模能力实现内容感知修复，有效去除缺陷并保留场景结构。为实现可扩展的高分辨率修复，采用分块策略并引入位置感知全局融合模块以维持跨块一致性；进一步设计频域增强模块提升纹理一致性，并构建分块一致推理框架缓解分块处理带来的块效应。此外，构建了一个包含分类缺陷模板、专业修复影片及真实合成退化的电影修复数据集。大量实验表明，本方法在结构一致性与整体质量上均优于现有方案，且显著降低内存开销，可在单张24GB显存GPU上完成高分辨率修复。代码与数据集将公开于https://anonymous.4open.science/r/HaineiFRDM。
原文摘要 · Abstract (English)
Existing film-restoration methods frequently fail under fast motion, producing limb disappearance and structural distortion due to inaccurate motion modeling. Moreover, high-resolution restoration under spatially-persistent and mixed defects remains insufficiently studied. We propose HaineiFRDM, a Film Restoration Diffusion Model that leverages the content modeling capability of diffusion models for content-aware restoration, removing defects while preserving scene structure.To enable scalable high-resolution restoration, we adopt a patch-wise strategy with position-aware global fusion modules to maintain cross-patch coherence. We further introduce a frequency-based module to enhance texture consistency and a patch-consistent inference framework to alleviate blocking artifacts introduced by patch-based processing.We also construct a film restoration dataset comprising categorized defect templates, professionally restored films, and realistic synthetic degradations.Extensive experiments demonstrate our superior restoration quality with strong structural consistency. Our design also reduces memory requirements, enabling high-resolution restoration on a single 24GB-VRAM GPU.Code and the dataset will be released at https://anonymous.4open.science/r/HaineiFRDM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。