Which is the Better Inpainted Image?Training Data Generation Without Any Manual Operations

• Published in: International Journal of Computer Vision Vol. 127; no. 11-12; pp. 1751 - 1766
• Main Authors: Isogawa, Mariko, Mikami, Dan, Takahashi, Kosuke, Iwai, Daisuke, Sato, Kosuke, Kimata, Hideaki
• Format: Journal Article
• Language: English
• Published: New York Springer Science and Business Media LLC 01.12.2019; Springer US; Springer; Springer Nature B.V
• Subjects: Algorithms; Annotations; Artificial Intelligence; Computer Imaging; Computer Science; Computer simulation; Image Processing and Computer Vision; Image quality; Masking; Pattern Recognition; Pattern Recognition and Graphics; Quality assessment; Training; Vision; Image inpainting; Image quality assessment (IQA); Learning to rank

This paper proposes a learning-based quality evaluation framework for inpainted results that does not require any subjectively annotated training data. Image inpainting, which removes and restores unwanted regions in images, is widely acknowledged as a task whose results are quite difficult to evalu...