Summary of Ai-generated Image Quality Assessment in Visual Communication, by Yu Tian et al.
AI-generated Image Quality Assessment in Visual Communication
by Yu Tian, Yixuan Li, Baoliang Chen, Hanwei Zhu, Shiqi Wang, Sam Kwong
First submitted to arxiv on: 20 Dec 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 paper aims to address the quality assessment of artificial intelligence-generated images (AIGIs) in real-world applications, particularly in visual communication. The authors introduce a novel database, AIGI-VC, which evaluates the communicability of AIGIs in the advertising field from the perspectives of information clarity and emotional interaction. The dataset comprises 2,500 images across 14 advertisement topics and 8 emotion types, featuring coarse-grained human preference annotations and fine-grained descriptions. By benchmarking various IQA methods and large multi-modal models on this dataset, the study reveals their strengths and weaknesses in predicting preferences, interpreting results, and reasoning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers created a special database to test how well AI-generated images work at showing information and evoking emotions in advertisements. They looked at 2,500 pictures across 14 topics and 8 emotional types. The database has two kinds of ratings: overall likes and detailed descriptions. By comparing different ways to judge image quality and big models that can learn from lots of data, the study shows what each method is good or bad at. |
Keywords
» Artificial intelligence » Multi modal
