用扩散先验修复复杂退化图像，提升视觉质量和任务性能
Exploiting Diffusion Prior for Task-driven Image Restoration
- 从低质量图像生成带轻微噪声的预修复图，直接利用扩散过程中的有用线索
- 仅用少量去噪步骤避免冗余细节干扰关键任务信息
- 在多种复杂退化场景下显著提升图像恢复效果和下游任务表现
任务驱动图像修复（TDIR）旨在缓解低质量输入导致的高层视觉任务性能下降。现有方法难以应对由多重复杂因素引起的退化，且恢复线索极少。为此，我们引入扩散先验这一强大自然图像先验。尽管扩散先验能生成视觉逼真结果，但如何保留任务相关细节仍具挑战，即使结合最新TDIR方法亦如此。为此，我们提出EDTR，有效利用扩散先验恢复任务相关细节。具体地，通过在像素误差基础上对低质量图像进行轻度预修复并添加微小噪声，直接引导扩散过程；同时采用少量去噪步骤，防止生成冗余细节稀释关键任务信息。实验表明，该方法显著提升多任务、多复杂退化场景下的任务性能与视觉质量。
原文摘要 · Abstract (English)
Task-driven image restoration (TDIR) has recently emerged to address performance drops in high-level vision tasks caused by low-quality (LQ) inputs. Previous TDIR methods struggle to handle practical scenarios in which images are degraded by multiple complex factors, leaving minimal clues for restoration. This motivates us to leverage the diffusion prior, one of the most powerful natural image priors. However, while the diffusion prior can help generate visually plausible results, using it to restore task-relevant details remains challenging, even when combined with recent TDIR methods. To address this, we propose EDTR, which effectively harnesses the power of diffusion prior to restore task-relevant details. Specifically, we propose directly leveraging useful clues from LQ images in the diffusion process by generating from pixel-error-based pre-restored LQ images with mild noise added. Moreover, we employ a small number of denoising steps to prevent the generation of redundant details that dilute crucial task-related information. We demonstrate that our method effectively utilizes diffusion prior for TDIR, significantly enhancing task performance and visual quality across diverse tasks with multiple complex degradations.
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。