通过像素级掩码优化轻量图像超分辨率，提升精度与效率
Pure-Pass: Fine-Grained, Adaptive Masking for Dynamic Token-Mixing Routing in Lightweight Image Super-Resolution
- 基于固定颜色中心点识别纯像素，实现精细空间掩码
- 在相似计算开销下，重建质量超越前代模型1.27dB PSNR
- 适合部署于资源受限的边缘设备，兼顾速度与画质
图像超分辨率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常因计算复杂度过高而难以实际部署。CAMixer是首个融合现有轻量级超分辨率方法优势的工作，提出内容感知混合器，根据内容恢复难度动态调度不同复杂度的令牌混合器。然而仍存在适应性差、掩码粒度粗、空间灵活性不足等问题。本文提出Pure-Pass（PP），一种像素级掩码机制，可识别纯像素并跳过其昂贵计算。PP利用固定颜色中心点对像素分类，实现细粒度、空间灵活的掩码，同时保持自适应能力。集成至当前先进模型ATD-light后，PP-ATD-light在仅节省相近计算量的前提下，重构质量优于CAMixer-ATD-light，PSNR提升1.27dB，参数效率更高。
原文摘要 · Abstract (English)
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.
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。