Summary of Neural Image Compression with Text-guided Encoding For Both Pixel-level and Perceptual Fidelity, by Hagyeong Lee et al.
Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity
by Hagyeong Lee, Minkyu Kim, Jun-Hyuk Kim, Seungeon Kim, Dokwan Oh, Jaeho Lee
First submitted to arxiv on: 5 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 This text-guided image compression algorithm achieves both high pixel-wise fidelity and perceptual quality by leveraging semantic information from text. The proposed framework uses text-adaptive encoding and training with a joint image-text loss function, avoiding decoding based on generative models. Experimental results show that the method outperforms baselines in terms of LPIPS, with room for further improvement using more carefully generated captions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates an algorithm that helps compress images while keeping them looking good. It uses text information to make sure the compression is done well, without relying on generative models that can produce different results each time. The results show that this method is better than others at compressing images and maintaining their quality. |
Keywords
* Artificial intelligence * Loss function
