WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency

Abstract

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 PixelShuffle operation and (2) implementing a multi-stage design for higher resolution tasks (4×). 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 and exhibiting higher parameter efficiency and throughput.