WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency

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-res...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Jeevan, Pranav, Nixon, Neeraj, Sethi, Amit
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 16.09.2024
Subjects
Discrete Wavelet Transform
Efficiency
Image enhancement
Image resolution
Mixers
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422