WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912095151325184 |
|---|---|
| author | Jeevan, Pranav Nixon, Neeraj Sethi, Amit |
| author_facet | Jeevan, Pranav Nixon, Neeraj Sethi, Amit |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10582 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency Jeevan, Pranav Nixon, Neeraj Sethi, Amit Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning I.2.10; I.4.0; I.4.1; I.4.2; I.4.6; I.4.7; I.4.8; I.4.9; I.4.10; I.2.10; I.5.1; I.5.2; I.5.4; I.4.3; I.4.4; I.4.5 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. |
| title | WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning I.2.10; I.4.0; I.4.1; I.4.2; I.4.6; I.4.7; I.4.8; I.4.9; I.4.10; I.2.10; I.5.1; I.5.2; I.5.4; I.4.3; I.4.4; I.4.5 |
| url | https://arxiv.org/abs/2409.10582 |