Summary of Gt-rain Single Image Deraining Challenge Report, by Howard Zhang and Yunhao Ba and Ethan Yang and Rishi Upadhyay and Alex Wong and Achuta Kadambi and Yun Guo and Xueyao Xiao and Xiaoxiong Wang and Yi Li and Yi Chang and Luxin Yan and Chaochao Zheng and Luping Wang and Bin Liu and Sunder Ali Khowaja and Jiseok Yoon and Ik-hyun Lee and Zhao Zhang and Yanyan Wei and Jiahuan Ren and Suiyi Zhao and Huan Zheng
GT-Rain Single Image Deraining Challenge Report
by Howard Zhang, Yunhao Ba, Ethan Yang, Rishi Upadhyay, Alex Wong, Achuta Kadambi, Yun Guo, Xueyao Xiao, Xiaoxiong Wang, Yi Li, Yi Chang, Luxin Yan, Chaochao Zheng, Luping Wang, Bin Liu, Sunder Ali Khowaja, Jiseok Yoon, Ik-Hyun Lee, Zhao Zhang, Yanyan Wei, Jiahuan Ren, Suiyi Zhao, Huan Zheng
First submitted to arxiv on: 18 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 The proposed paper reviews the results of the GT-Rain challenge on single image deraining at the UG2+ workshop at CVPR 2023, which aimed to study real-world rainy scenarios, provide a novel dataset, and spark innovative ideas for single-image deraining methods. The competition evaluated submissions trained on the GT-Rain dataset on an extended dataset with 15 additional scenes. The challenge was comprised of real rainy images and ground truth images captured after rainfall ceased. A total of 275 participants registered, with 55 competing in the final testing phase. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The study aims to improve single-image deraining methods by providing a novel real-world rainy image dataset. Participants submitted models trained on this dataset and evaluated them on an extended dataset. The results from the challenge show promise for developing more effective single-image deraining techniques. |
