arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.08736cs.CV
收藏

面向任务的高效任意尺度图像超分辨率动态Transformer

Task-Aware Dynamic Transformer for Efficient Arbitrary-Scale Image Super-Resolution

School of Statistics and Data Science, Nankai University(南开大学统计与数据科学学院);College of Computer Science, Nankai University(南开大学计算机学院);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院);Tencent Data Platform(腾讯云与智慧产业事业群数据平台部);Zhejiang University(浙江大学);Systems Engineering Research Institute, China State Shipbuilding Corporation Limited(中国船舶重工集团公司系统工程研究院);Guangdong Provincial Key Laboratory of Big Data Computing, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)广东省大数据计算重点实验室)

Tianyi Xu, Yiji Zhou, Xiaotao Hu, Kai Zhang, Anran Zhang, Xingye Qiu, Jun Xu

AI总结:

本文提出面向任务的动态Transformer(TADT),通过多尺度主干网络和任务感知路由控制器根据输入和尺度自适应选择推理路径,在保持最先进任意尺度超分辨率性能的同时有效降低计算成本。

摘要:

任意尺度超分辨率(ASSR)旨在学习一个单一模型,用于实现任意放大倍数下的图像超分辨率。现有的ASSR网络通常由现成的尺度无关特征提取器和任意尺度上采样器组成。这些特征提取器往往使用固定的网络架构来处理不同的ASSR推理任务,每个任务由输入图像和上采样尺度共同决定。然而,这忽略了不同推理场景下超分辨率的难度差异,即简单图像或较小的SR尺度比困难图像或较大的SR尺度所需的计算量更少。为了应对这种难度可变性,本文提出了一种面向任务的动态Transformer(TADT),作为输入自适应的特征提取器,以实现高效的图像ASSR。我们的TADT包含一个基于多尺度Transformer块(MSTB)组构建的多尺度特征提取主干网络,以及一个面向任务的路由控制器(TARC)。TARC根据输入图像和SR尺度预测特征提取主干网络内的推理路径,具体选择相应的MSTB。推理路径的预测由一个新的损失函数引导,以权衡SR精度与效率。实验表明,当与三种流行的任意尺度上采样器结合使用时,与主流特征提取器相比,我们的TADT在实现最先进ASSR性能的同时,计算成本相对更低。代码将公开发布。

英文摘要:

Arbitrary-scale super-resolution (ASSR) aims to learn a single model for image super-resolution at arbitrary magnifying scales. Existing ASSR networks typically comprise an off-the-shelf scale-agnostic feature extractor and an arbitrary scale upsampler. These feature extractors often use fixed network architectures to address different ASSR inference tasks, each of which is characterized by an input image and an upsampling scale. However, this overlooks the difficulty variance of super-resolution on different inference scenarios, where simple images or small SR scales could be resolved with less computational effort than difficult images or large SR scales. To tackle this difficulty variability, in this paper, we propose a Task-Aware Dynamic Transformer (TADT) as an input-adaptive feature extractor for efficient image ASSR. Our TADT consists of a multi-scale feature extraction backbone built upon groups of Multi-Scale Transformer Blocks (MSTBs) and a Task-Aware Routing Controller (TARC). The TARC predicts the inference paths within feature extraction backbone, specifically selecting MSTBs based on the input images and SR scales. The prediction of inference path is guided by a new loss function to trade-off the SR accuracy and efficiency. Experiments demonstrate that, when working with three popular arbitrary-scale upsamplers, our TADT achieves state-of-the-art ASSR performance when compared with mainstream feature extractors, but with relatively fewer computational costs. The code will be publicly released.

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。

↑