상세정보
학술지
Quality Prediction on Deep Generative Images
- 저자
- 고현석, 이대열, 조승현, 앨런 보빅
- 발행일
- 202004
- 출처
- IEEE Transactions on Image Processing, v.29, pp.5964-5979
- ISSN
- 1057-7149
- 출판사
- IEEE
- 협약과제
- 19HR2500, [통합과제] 초실감 테라미디어를 위한 AV부호화 및 LF미디어 원천기술 개발, 최진수
- 초록
- In recent years, deep neural networks have been utilized in a wide variety of applications including image generation. In particular, generative adversarial networks (GANs) are able to produce highly realistic pictures as part of tasks such as image compression. As with standard compression, it is desirable to be able to automatically assess the perceptual quality of generative images to monitor and control the encode process. However, existing image quality algorithms are ineffective on GAN generated content, especially on textured regions and at high compressions. Here we propose a new 'naturalness'-based image quality predictor for generative images. Our new GAN picture quality predictor is built using a multi-stage parallel boosting system based on structural similarity features and measurements of statistical similarity. To enable model development and testing, we also constructed a subjective GAN image quality database containing (distorted) GAN images and collected human opinions of them. Our experimental results indicate that our proposed GAN IQA model delivers superior quality predictions on the generative image datasets, as well as on traditional image quality datasets.
- KSP 제안 키워드
- Deep neural network(DNN), Image Compression, Image datasets, Image generation, Monitor and Control, Multi-stage, Perceptual Quality, Picture quality, Quality prediction, Structure Similarity Index measure(SSIM), Textured regions