DeepWSD : Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space

Xingran LIAO, Baoliang CHEN, Hanwei ZHU, Shiqi WANG, Mingliang ZHOU, Sam KWONG

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

5 Citations (Scopus)


Existing deep learning-based full-reference IQA (FR-IQA) models usually predict the image quality in a deterministic way by explicitly comparing the features, gauging how severely distorted an image is by how far the corresponding feature lies from the space of the reference images. Herein, we look at this problem from a different viewpoint and propose to model the quality degradation in perceptual space from a statistical distribution perspective. As such, the quality is measured based upon the Wasserstein distance in the deep feature domain. More specifically, the 1D Wasserstein distance at each stage of the pre-trained VGG network is measured, based on which the final quality score is performed. The deep Wasserstein distance (DeepWSD) performed on features from neural networks enjoys better interpretability of the quality contamination caused by various types of distortions and presents an advanced quality prediction capability. Extensive experiments and theoretical analysis show the superiority of the proposed DeepWSD in terms of both quality prediction and optimization. The implementation of our method is publicly available at
Original languageEnglish
Title of host publicationProceedings of the 30th ACM International Conference on Multimedia
PublisherAssociation for Computing Machinery
ISBN (Print)9781450392037
Publication statusPublished - Oct 2022
Externally publishedYes
EventThe 30th ACM International Conference on Multimedia - Lisbon, Portugal
Duration: 10 Oct 202214 Oct 2022


ConferenceThe 30th ACM International Conference on Multimedia

Bibliographical note

This work was supported in part by the Key Project of Science and Technology Innovation 2030 supported by the Ministry of Science and Technology of China (Grant No. 2018AAA0101301), the National Natural Science Foundation of China Grant 61672443, 62022002 and 62176027, in part by Hong Kong GRF - RGC General Research Fund 9042816 (CityU 11209819) and 9042958 (CityU 11203820). Also, this work is supported by the Hong Kong Innovation and Technology Commission (InnoHK Project CIMDA).


  • full-reference IQA
  • statistical model for image representation
  • Wasserstein distance


Dive into the research topics of 'DeepWSD : Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space'. Together they form a unique fingerprint.

Cite this