Indexed by:
Abstract:
Existing NR-IIQA (no reference-based inpainted image quality assessment) algorithms assess the quality of an inpainted image via artificially designed unnaturalness expression, which often fail to capture inpainted artifacts. This paper presents a new deep rank learning-based method for NR-IIQA. The model adopts a siamese deep architecture, which takes a pair of inpainted images as input and outputs their rank order. Each branch utilizes a CNN structure to capture the global structure coherence and a patch-wise coherence assessment module (PCAM) to depict the local color and texture consistency in an inpainted image. To train the deep model, we construct a new dataset, which contains thousands of pairs of inpainted images with ground-truth quality ranking labels. Rich ablation studies are conducted to verify the key modules of the proposed architecture. Comparative experimental results demonstrate that our method outperforms existing NR-IIQA metrics in evaluating both inpainted images and inpainting algorithms.
Keyword:
Reprint Author's Address:
Email:
Source :
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
ISSN: 1047-3203
Year: 2021
Volume: 78
2 . 6 0 0
JCR@2022
ESI Discipline: COMPUTER SCIENCE;
ESI HC Threshold:87
JCR Journal Grade:2
Cited Count:
WoS CC Cited Count: 2
SCOPUS Cited Count: 1
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 0
Affiliated Colleges: