Summary of Sdi-net: Toward Sufficient Dual-view Interaction For Low-light Stereo Image Enhancement, by Linlin Hu et al.
SDI-Net: Toward Sufficient Dual-View Interaction for Low-light Stereo Image Enhancement
by Linlin Hu, Ao Sun, Shijie Hao, Richang Hong, Meng Wang
First submitted to arxiv on: 20 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); 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 approach for low-light stereo image enhancement, called SDI-Net, which leverages the interaction between left and right views to produce superior results. The method consists of two encoder-decoder pairs that learn the mapping function from low-light images to normal-light images. A key innovation is the Cross-View Sufficient Interaction Module (CSIM), which exploits the correlations between binocular views via an attention mechanism. The paper demonstrates the effectiveness of SDI-Net on public datasets, outperforming related methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study aims to improve low-light image enhancement by considering information from multiple views. Current methods don’t fully use this information, leading to poor results. To fix this, researchers developed special methods for low-light stereo images, which do a better job. But even these methods have limitations. The new method, called SDI-Net, tries to overcome these limits by letting the different views work together more effectively. The paper shows that this approach works well on certain datasets and is better than other methods. |
Keywords
» Artificial intelligence » Attention » Encoder decoder
