EUVIMEDEUVIMED entdecken
Crossref

Deep Underwater Image Quality Assessment With Explicit Degradation Awareness Embedding

Qiuping Jiang, Yuese Gu, Zongwei Wu, Chongyi Li, Huan Xiong, Feng Shao, Zhihua Wang

IEEE Transactions on Image Processing · 2025 · 34 · 1297-1310

DOI: 10.1109/tip.2025.3539477 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Qiuping Jiang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: Natural Science Foundation of Zhejiang, National Natural Science Foundation of China, Natural Science Foundation of Ningbo Municipality.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater Image Quality Assessment (UIQA) is currently an area of intensive research interest. Existing deep learning-based UIQA models always learn a deep neural network to directly map the input degraded underwater image into a final quality score via end-to-end training. However, a wide variety of image contents or distortion types may correspond to the same quality score, making it challenging to train such a deep model merely with a single subjective quality score as supervision. An intuitive idea to solve this problem is to exploit more detailed degradation-aware information as supplementary guidance to facilitate model learning. In this paper, we devise a novel deep UIQA model with Explicit Degradation Awareness embedding, i.e., EDANet. To train the EDANet, a two-stage training strategy is adopted. First, a tailored Degradation Information Discovery subnetwork (DIDNet) is pre-trained to infer a residual map between the input degraded underwater image and its pseudoreference counterpart. The inferred residual map explicitly characterizes the local degradation of the input underwater image. The intermediate feature representations on the decoder side of DIDNet are then embedded into the Degradation-guided Quality Evaluation subnetwork (DQENet), which significantly enhances the feature characterization capability with higher degradation awareness for quality prediction. The superiority of our EDANet against 18 state-of-the-art methods has been well demonstrated by extensive comparisons on two benchmark datasets. The source code of our EDANet is available at https://github.com/yia-yuese/EDANet.

Förderung

  • Natural Science Foundation of Zhejiang
  • National Natural Science Foundation of China
  • Natural Science Foundation of Ningbo Municipality
  • Key Research and Development Program of Ningbo
  • "Leading Goose" Research and Development Program of Zhejiang

Zitieren

APA

Jiang, Q., Gu, Y., Wu, Z., Li, C., Xiong, H., Shao, F., & Wang, Z. (2025). Deep Underwater Image Quality Assessment With Explicit Degradation Awareness Embedding. IEEE Transactions on Image Processing, 34, 1297-1310. https://doi.org/10.1109/tip.2025.3539477

Vancouver

Jiang Q, Gu Y, Wu Z, Li C, Xiong H, Shao F, et al. Deep Underwater Image Quality Assessment With Explicit Degradation Awareness Embedding. IEEE Transactions on Image Processing. 2025;34:1297-1310. doi:10.1109/tip.2025.3539477

BibTeX
@article{Jiang2025,
  author = {Jiang, Qiuping and Gu, Yuese and Wu, Zongwei and Li, Chongyi and Xiong, Huan and Shao, Feng and Wang, Zhihua},
  title = {Deep Underwater Image Quality Assessment With Explicit Degradation Awareness Embedding},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  volume = {34},
  pages = {1297--1310},
  doi = {10.1109/tip.2025.3539477}
}
Kostenlos starten →