Pure-Pass：面向轻量级图像超分辨率的动态Token混合路由的细粒度自适应掩码
Pure-Pass: Fine-Grained, Adaptive Masking for Dynamic Token-Mixing Routing in Lightweight Image Super-Resolution
AI总结：
本文提出Pure-Pass（PP）像素级掩码机制，通过固定颜色中心点分类纯净像素并免除其计算开销，解决了轻量级图像超分辨率中掩码粒度粗和空间灵活性不足的问题，在最小开销下提升了SR性能。
摘要：
图像超分辨率（SR）旨在从低分辨率图像重建高分辨率图像，但基于深度学习的方法的计算复杂度往往阻碍了实际部署。CAMixer是整合现有轻量级SR方法优势的先驱工作，提出了一种内容感知混合器，根据内容恢复的难度路由不同复杂度的token混合器。然而，仍存在若干局限性，如适应性差、掩码粒度粗和空间灵活性不足等。我们提出Pure-Pass（PP），一种像素级掩码机制，可识别纯净像素并使其免除昂贵的计算。PP利用固定的颜色中心点将像素分为不同类别，在保持自适应灵活性的同时实现细粒度、空间灵活的掩码。集成到最先进的ATD-light模型后，PP-ATD-light以最小开销实现了卓越的SR性能，在节省相似计算量的情况下，在重建质量和参数效率上均优于CAMixer-ATD-light。
英文摘要：
Image Super-Resolution (SR) aims to reconstruct high-resolution images from low-resolution counterparts, but the computational complexity of deep learning-based methods often hinders practical deployment. CAMixer is the pioneering work to integrate the advantages of existing lightweight SR methods and proposes a content-aware mixer to route token mixers of varied complexities according to the difficulty of content recovery. However, several limitations remain, such as poor adaptability, coarse-grained masking and spatial inflexibility, among others. We propose Pure-Pass (PP), a pixel-level masking mechanism that identifies pure pixels and exempts them from expensive computations. PP utilizes fixed color center points to classify pixels into distinct categories, enabling fine-grained, spatially flexible masking while maintaining adaptive flexibility. Integrated into the state-of-the-art ATD-light model, PP-ATD-light achieves superior SR performance with minimal overhead, outperforming CAMixer-ATD-light in reconstruction quality and parameter efficiency when saving a similar amount of computation.
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。
