English

WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency

Image and Video Processing 2024-10-31 v3 Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning

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 pixel shuffle operation and (2) implementing a multistage design for higher resolution tasks (4×4\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.

Keywords

Cite

@article{arxiv.2409.10582,
  title  = {WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency},
  author = {Pranav Jeevan and Neeraj Nixon and Amit Sethi},
  journal= {arXiv preprint arXiv:2409.10582},
  year   = {2024}
}

Comments

10 pages. Accepted in AAAI 2025. arXiv admin note: text overlap with arXiv:2307.00430

R2 v1 2026-06-28T18:46:41.177Z