In this article, we address the degraded image super-resolution problem in a multi-task learning (MTL) manner. To better share representations between multiple tasks, we propose an all-in-one collaboration framework (ACF) with a learnable “junction” unit to handle two major problems that exist in MTL—“How to share” and “How much to share.” Specifically, ACF consists of a sharing phase and a reconstruction phase. Considering the intrinsic characteristic of multiple image degradations, we propose to first deal with the compression artifact, motion blur, and spatial structure information of the input image in parallel under a three-branch architecture in the sharing phase. Subsequently, in the reconstruction phase, we up-sample the previous features for high-resolution image reconstruction with a channel-wise and spatial attention mechanism. To coordinate two phases, we introduce a learnable “junction” unit with a dual-voting mechanism to selectively filter or preserve shared feature representations that come from sharing phase, learning an optimal combination for the following reconstruction phase. Finally, a curriculum learning-based training scheme is further proposed to improve the convergence of the whole framework. Extensive experimental results on synthetic and real-world low-resolution images show that the proposed all-in-one collaboration framework not only produces favorable high-resolution results while removing serious degradation, but also has high computational efficiency, outperforming state-of-the-art methods. We also have applied ACF to some image-quality sensitive practical task, such as pose estimation, to improve estimation accuracy of low-resolution images.

中文翻译：

---

基于多任务学习的降级图像超分辨率一体化协作框架

在本文中，我们以多任务学习（MTL）的方式解决了退化的图像超分辨率问题。为了更好地在多个任务之间共享表示，我们提出了一个多合一协作框架（ACF），它带有一个可学习的“连接”单元来处理 MTL 中存在的两个主要问题——“如何共享”和“共享多少”。 ” 具体来说，ACF 由一个分享相和一个重建阶段。考虑到多个图像退化的内在特征，我们建议首先在三分支架构下并行处理输入图像的压缩伪影、运动模糊和空间结构信息。分享阶段。随后，在重建阶段，我们使用通道和空间注意机制对先前的特征进行上采样以进行高分辨率图像重建。为了协调两个阶段，我们引入了一个具有双重投票机制的可学习“连接”单元，以选择性地过滤或保留来自分享阶段，学习以下的最佳组合重建阶段。最后，进一步提出了基于课程学习的培训方案，以提高整个框架的收敛性。在合成和真实世界低分辨率图像上的大量实验结果表明，所提出的一体化协作框架不仅在消除严重退化的同时产生了良好的高分辨率结果，而且具有很高的计算效率，优于 state-of-the -艺术方法。我们还将 ACF 应用于一些对图像质量敏感的实际任务，例如姿态估计，以提高低分辨率图像的估计精度。