Summary of Gabor-guided Transformer For Single Image Deraining, by Sijin He et al.
Gabor-guided transformer for single image deraining
by Sijin He, Guangfeng Lin
First submitted to arxiv on: 12 Mar 2024
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 paper proposes a novel transformer-based approach for single-image deraining called Gabor-guided transformer (Gabformer). The authors leverage self-attention mechanisms to capture global information, but also incorporate local texture features using the Gabor filter. This enables Gabformer to effectively remove rain while preserving high-frequency details, which is crucial for image fidelity. Experimental results on benchmarks show that Gabformer outperforms state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to see a clear picture of a rainy day, but the rain makes it hard to recognize what’s in the photo. This problem is called image deraining, and researchers have been working on ways to make images clearer again. Some machines use special kinds of networks (called CNNs) that are good at recognizing patterns, but they can’t capture everything. Other methods try to fix this by using a different kind of network with attention, which helps the machine focus on important parts of the image. However, these methods often distort small details that make the image look blurry. To solve this problem, scientists have come up with a new way called Gabformer, which uses the Gabor filter to help machines understand texture and patterns in images better. This makes it possible for Gabformer to remove rain from photos effectively while keeping the important details sharp. |
Keywords
» Artificial intelligence » Attention » Self attention » Transformer
