GIQA: Generated Image Quality Assessment

By Shuyang Gu, Jianmin Bao, Dong Chen, Fang Wen. 2020

104 citations recorded by the source corpus.

Generative adversarial networks (GANs) have achieved impressive results today, but not all generated images are perfect. A number of quantitative criteria have recently emerged for generative model, but none of them are designed for a single generated image. In this paper, we propose a new research topic, Generated Image Quality Assessment (GIQA), which quantitatively evaluates the quality of each generated image. We introduce three GIQA algorithms from two perspectives: learning-based and data-based. We evaluate a number of images generated by various recent GAN models on different datasets and demonstrate that they are consistent with human assessments. Furthermore, GIQA is available to many applications, like separately evaluating the realism and diversity of generative models, and enabling online hard negative mining (OHEM) in the training of GANs to improve the results.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Lu Yuan
2. Dong Chen
3. Luc Van Gool
4. Xiaogang Wang
5. Fang Wen
6. Jianmin Bao
7. Ming-Hsuan Yang
8. Dacheng Tao

In Evaluation & Benchmarks

1. Lu Yuan
2. Fang Wen
3. Shuyang Gu
4. Baining Guo
5. Dong Chen
6. Dongdong Chen
7. Jianmin Bao

Citations in the corpus

• Vector Quantized Diffusion Model for Text-to-Image Synthesis (2021, background): “In the past few years, Generative Adversarial Networks (GANs) [18] have shown promising results on many tasks [19–21],, especially text-to-image generation [5, 8, 9, 14, 17, 25, 27, 31–34, 38, 43, 44, 50, 51, 58, 60–63, 67–73].”
• StyleSwin: Transformer-based GAN for High-resolution Image Generation (2021, background): “While early attempts focus on stabilizing the training dynamics via proper regularization [15,16,36,46,47] or adversarial loss designs [2, 25, 39, 45], remarkable performance leaps in recent prominent works mainly attribute to the architectural modifications that aim for stronger modeling capacity, ”
• Paint by Example: Exemplar-based Image Editing with Diffusion Models (2022, background): “2) Quality Score(QS) [17], which aims to evaluate the authenticity of each single image.”