Summary of Tsnet:a Two-stage Network For Image Dehazing with Multi-scale Fusion and Adaptive Learning, by Xiaolin Gong and Zehan Zheng and Heyuan Du
TSNet:A Two-stage Network for Image Dehazing with Multi-scale Fusion and Adaptive Learning
by Xiaolin Gong, Zehan Zheng, Heyuan Du
First submitted to arxiv on: 3 Apr 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 The proposed two-stage image dehazing network, TSNet, aims to improve the generalization capabilities of deep learning-based image dehazing methods. The network consists of a multi-scale fusion module (MSFM) and an adaptive learning module (ALM). MSFM enhances feature integration at different frequencies, reducing differences between inputs and learning objectives. ALM actively learns regions of interest in images, restoring texture details more effectively. TSNet is designed as a two-stage network, where the first stage performs dehazing and the second stage improves artifacts and color distortion. The learning objective is changed from ground truth images to opposite fog maps, improving learning efficiency. Extensive experiments demonstrate superior dehazing performance on synthetic and real-world datasets compared to state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Image dehazing has been a challenging task for deep learning-based methods. A new network called TSNet is proposed to improve the generalization capabilities of these methods. The network consists of two stages: one for dehazing and another to fix any remaining issues like artifacts and color distortion. This approach leads to better results than previous state-of-the-art methods. |
Keywords
» Artificial intelligence » Deep learning » Generalization
