Summary of Crossdehaze: Scaling Up Image Dehazing with Cross-data Vision Alignment and Augmentation, by Yukai Shi et al.
CrossDehaze: Scaling Up Image Dehazing with Cross-Data Vision Alignment and Augmentation
by Yukai Shi, Zhipeng Weng, Yupei Lin, Cidan Shi, Xiaojun Yang, Liang Lin
First submitted to arxiv on: 20 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multimedia (cs.MM); Image and Video Processing (eess.IV)
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 method to improve image dehazing by addressing the domain gap between different datasets. The approach involves internal and external data augmentation, which allows the model to learn more robust features and exploit local information within images. The authors demonstrate the effectiveness of their method by training on both the Natural Image Dataset (NID) and the Remote Sensing Image Dataset (RSID), showing that it significantly outperforms other advanced methods in dehazing and produces dehazed images closest to real haze-free images. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to make pictures clearer by removing fog or haze. The problem is that most previous methods didn’t work well because they were trained on different types of images, which caused them to not perform well on other types. To fix this, the authors came up with a new method that combines two ways to improve image quality: internal and external data augmentation. This allows the model to learn more details from each picture and remove haze more effectively. The results show that their method is better than others at removing haze and produces images that are very close to what they would look like without haze. |
Keywords
* Artificial intelligence * Data augmentation
