arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.06709cs.CV
收藏

Review Learning：推进一体化超高清图像复原训练方法

Review Learning: Advancing All-in-One Ultra-High-Definition Image Restoration Training Method

Fuzhou University（福州大学）；Sun Yat-sen University（中山大学）；University of Science and Technology of China（中国科学技术大学）

Xin Su, Zhuoran Zheng, Chen Wu

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对一体化超高清图像复原训练中多退化目标杂乱导致的信息污染问题，提出Review Learning训练范式，结合顺序训练与回顾机制提升模型多退化处理能力，同时设计了可在消费级GPU上高效处理4K图像的轻量通用复原网络。

摘要：

一体化图像复原任务正变得愈发重要，尤其是针对超高清（UHD）图像的任务。现有的一体化超高清图像复原方法通常通过引入提示（prompt）或针对不同退化类型定制动态网络来提升模型性能。这一思路在推理阶段或许较为友好，但在训练阶段，由于模型在一个轮次（epoch）中会接触到多张质量各异的退化图像，这些杂乱的学习目标可能会对模型造成信息污染。为解决这一问题，我们提出了一种适用于通用图像复原模型的新型训练范式，将其命名为**Review Learning**，该范式能让图像复原模型在无需先验知识和提示的前提下，具备处理多种类型退化的能力。该方法首先在多个退化数据集上对图像复原模型进行顺序训练，并结合一种回顾机制，强化图像复原模型对前几类退化数据集的记忆。此外，我们还设计了一个轻量级通用图像复原网络，该网络可在单张消费级GPU上高效处理4K（$3840 \ imes 2160$）分辨率的退化图像推理。

英文摘要：

All-in-one image restoration tasks are becoming increasingly important, especially for ultra-high-definition (UHD) images. Existing all-in-one UHD image restoration methods usually boost the model's performance by introducing prompt or customized dynamized networks for different degradation types. For the inference stage, it might be friendly, but in the training stage, since the model encounters multiple degraded images of different quality in an epoch, these cluttered learning objectives might be information pollution for the model. To address this problem, we propose a new training paradigm for general image restoration models, which we name \textbf{Review Learning}, which enables image restoration models to be capable enough to handle multiple types of degradation without prior knowledge and prompts. This approach begins with sequential training of an image restoration model on several degraded datasets, combined with a review mechanism that enhances the image restoration model's memory for several previous classes of degraded datasets. In addition, we design a lightweight all-purpose image restoration network that can efficiently reason about degraded images with 4K ($3840 \times 2160$) resolution on a single consumer-grade GPU.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑