WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency (Student Abstract)
Pranav Jeevan, Neeraj Nixon, Amit Sethi
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 (4x). 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.
BibTeX
@article{Jeevan_Nixon_Sethi_2025, title={WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency (Student Abstract)}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35262}, DOI={10.1609/aaai.v39i28.35262}, abstractNote={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 (4x). 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.}, number={28}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Jeevan, Pranav and Nixon, Neeraj and Sethi, Amit}, year={2025}, month={Apr.}, pages={29390-29392} }