• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Meng, Xiangdong (Meng, Xiangdong.) | Ma, Wei (Ma, Wei.) | Li, Chunhu (Li, Chunhu.) | Mi, Qing (Mi, Qing.)

Indexed by:

EI Scopus SCIE

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:

Image quality assessment Siamese network Rank learning Image inpainting

Author Community:

  • [ 1 ] [Meng, Xiangdong]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Ma, Wei]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Li, Chunhu]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Mi, Qing]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

Reprint Author's Address:

  • [Ma, Wei]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

Show more details

Related Keywords:

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:

Online/Total:746/5309268
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.