让压缩图增强模型在多次处理后仍保持画质，不越修越差
Breaking the Multi-Enhancement Bottleneck: Domain-Consistent Quality Enhancement for Compressed Images
- 通过域一致性设计，使增强模型首次修复图像后不再被后续增强破坏
- 多轮增强下仍能保持视觉质量与保真度，性能远超传统方法
- 适用于现有模型改造，适合实际通信场景中的连续图像处理
质量增强方法广泛应用于视觉通信链路中以缓解压缩图像的伪影。理想情况下，这些方法应能在已经历前期增强的图像上依然表现稳健。我们称此场景为多增强，它泛化了图像压缩中的多生成场景。然而，当前质量增强方法在多增强场景下会出现严重退化。为此，我们提出一种新适配方法，将现有质量增强模型转化为域一致模型。具体而言，该方法在首次增强时将低质量压缩图像还原至自然域内的高质量图像，并确保后续增强不会破坏此质量。大量实验验证了方法的有效性，表明多种现有模型均可成功适配，在多增强场景中同时保持保真度与感知质量。
原文摘要 · Abstract (English)
Quality enhancement methods have been widely integrated into visual communication pipelines to mitigate artifacts in compressed images. Ideally, these quality enhancement methods should perform robustly when applied to images that have already undergone prior enhancement during transmission. We refer to this scenario as multi-enhancement, which generalizes the well-known multi-generation scenario of image compression. Unfortunately, current quality enhancement methods suffer from severe degradation when applied in multi-enhancement. To address this challenge, we propose a novel adaptation method that transforms existing quality enhancement models into domain-consistent ones. Specifically, our method enhances a low-quality compressed image into a high-quality image within the natural domain during the first enhancement, and ensures that subsequent enhancements preserve this quality without further degradation. Extensive experiments validate the effectiveness of our method and show that various existing models can be successfully adapted to maintain both fidelity and perceptual quality in multi-enhancement scenarios.
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。