Summary of Wavemixsr: a Resource-efficient Neural Network For Image Super-resolution, by Pranav Jeevan et al.
WaveMixSR: A Resource-efficient Neural Network for Image Super-resolution
by Pranav Jeevan, Akella Srinidhi, Pasunuri Prathiba, Amit Sethi
First submitted to arxiv on: 1 Jul 2023
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper proposes a novel neural network architecture, WaveMixSR, for image super-resolution. Unlike transformer-based models, which require significant computational resources due to their quadratic complexity, WaveMixSR leverages the inductive bias of convolutions and the lossless token-mixing property of wavelet transforms to achieve competitive performance with fewer resources and training data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary WaveMixSR is a new approach for image super-resolution that doesn’t unroll the image as a sequence of pixels or patches. Instead, it uses a 2D-discrete wavelet transform for spatial token-mixing. This allows WaveMixSR to achieve better results while needing less training data and computational resources. |
Keywords
* Artificial intelligence * Neural network * Super resolution * Token * Transformer
