WaveMixSR-V2用像素重组替代转置卷积，提升超分辨率效率与性能。
WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency
- 用像素重组替代转置卷积，减少参数量并加快推理速度。
- 在4倍超分辨率任务中表现超越现有模型，BSD100上达新纪录。
- 适合需要高效部署的实时图像超分辨率场景。
单图像超分辨率近年主要依赖令牌混合器与Transformer架构。WaveMixSR采用二维离散小波变换进行空间令牌混合，在保持资源高效的同时取得优异性能。本文提出升级版WaveMixSR-V2：（1）以像素重组替代传统转置卷积；（2）引入多阶段设计以支持更高分辨率（4×）任务。实验表明，该模型在多个超分辨率任务中表现领先，于BSD100数据集达到当前最优水平，同时参数更少、延迟更低、吞吐更高。代码已开源：https://github.com/pranavphoenix/WaveMixSR。
原文摘要 · Abstract (English)
Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spatial token mixing, achieving superior performance in super-resolution tasks with remarkable resource efficiency. In this work, we present an enhanced version of the WaveMixSR architecture by (1) replacing the traditional transpose convolution layer with a pixel shuffle operation and (2) implementing a multistage design for higher resolution tasks ($4\times$). Our experiments demonstrate that our enhanced model -- WaveMixSR-V2 -- outperforms other architectures in multiple super-resolution tasks, achieving state-of-the-art for the BSD100 dataset, while also consuming fewer resources, exhibits higher parameter efficiency, lower latency and higher throughput. Our code is available at https://github.com/pranavphoenix/WaveMixSR.
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。