首个可自动生成多种复杂图像退化效果的通用模型。
Towards a Universal Image Degradation Model via Content-Degradation Disentanglement
- 通过解耦内容与退化特征，自动分离均匀与非均匀退化成分。
- 在电影颗粒模拟和盲图像恢复任务中表现准确且适应性强。
- 无需人工调参，适合图像修复、艺术效果生成等场景。
图像退化合成在图像修复、艺术效果模拟等多种应用中具有重要意义。现有模型通常仅支持特定或有限类型的退化，需用户手动设置参数，难以泛化到新退化类型或新任务。本文提出首个通用退化模型，可合成包含均匀（全局）与非均匀（空间变化）成分的复杂真实退化效果。该模型自动提取并解耦均匀与非均匀退化特征，并利用这些特征进行无干预的退化合成。提出一种基于压缩的解耦方法，以分离图像中的退化信息；设计两个新颖模块，用于提取和融合非均匀退化成分，以建模复杂退化中的空间变化特性。实验表明，该模型在电影颗粒模拟和盲图像恢复任务中具备高精度与强适应性。项目演示视频、代码及数据集将发布于 github.com/yangwenbo99/content-degradation-disentanglement。
原文摘要 · Abstract (English)
Image degradation synthesis is highly desirable in a wide variety of applications ranging from image restoration to simulating artistic effects. Existing models are designed to generate one specific or a narrow set of degradations, which often require user-provided degradation parameters. As a result, they lack the generalizability to synthesize degradations beyond their initial design or adapt to other applications. Here we propose the first universal degradation model that can synthesize a broad spectrum of complex and realistic degradations containing both homogeneous (global) and inhomogeneous (spatially varying) components. Our model automatically extracts and disentangles homogeneous and inhomogeneous degradation features, which are later used for degradation synthesis without user intervention. A disentangle-by-compression method is proposed to separate degradation information from images. Two novel modules for extracting and incorporating inhomogeneous degradations are created to model inhomogeneous components in complex degradations. We demonstrate the model's accuracy and adaptability in film-grain simulation and blind image restoration tasks. The demo video, code, and dataset of this project will be released at github.com/yangwenbo99/content-degradation-disentanglement.
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。