Structure-preserving image smoothing via contrastive learning

Dingkun ZHU, Weiming WANG*, Xue XUE, Haoran XIE, Gary CHENG, Fu Lee WANG

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

2 Citations (Scopus)

Abstract

Image smoothing is an important processing operation that highlights low-frequency structural parts of an image and suppresses the noise and high-frequency textures. In the paper, we post an intriguing question of how to combine the paired unsmoothed/smoothed images and meaningful edge information to improve the performance of image smoothing. To this end, we propose a structure-preserving image smoothing network, which consists of a main interpreter (MI) and an edge map extractor (EME). The network is trained via contrastive learning on the extended BSD500 dataset. In addition, an edge-aware total variation loss function is utilized to distinguish between non-edge regions and edge maps via a pre-trained EME module, therefore improving the capability of structure preservation. In order to maintain the consistency in structure and background brightness, the outputs from MI are used as anchors for a ternary loss in 1:1 paired positive and negative samples. Experiments on different datasets show that our network outperforms state-of-the-art image smoothing methods in terms of SSIM and PSNR.
Original languageEnglish
JournalVisual Computer
Early online date30 May 2023
DOIs
Publication statusE-pub ahead of print - 30 May 2023

Bibliographical note

Funding Information:
The work described in this paper was supported by Hong Kong Metropolitan University Research Grant (No. RD/2021/09).

Publisher Copyright:
© 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Keywords

  • Contrastive learning
  • Edge map extractor
  • Image smoothing
  • Main interpreter
  • Structure preservation

Fingerprint

Dive into the research topics of 'Structure-preserving image smoothing via contrastive learning'. Together they form a unique fingerprint.

Cite this