Addressing Domain Discrepancy: A Dual-branch Collaborative Model to Unsupervised Dehazing
Although synthetic data can alleviate acquisition challenges in image dehazing tasks, it also introduces the problem of domain bias when dealing with small-scale data. This paper proposes a novel dual-branch collaborative unpaired dehazing model (DCM-dehaze) to address this issue. The proposed metho...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Although synthetic data can alleviate acquisition challenges in image
dehazing tasks, it also introduces the problem of domain bias when dealing with
small-scale data. This paper proposes a novel dual-branch collaborative
unpaired dehazing model (DCM-dehaze) to address this issue. The proposed method
consists of two collaborative branches: dehazing and contour constraints.
Specifically, we design a dual depthwise separable convolutional module (DDSCM)
to enhance the information expressiveness of deeper features and the
correlation to shallow features. In addition, we construct a bidirectional
contour function to optimize the edge features of the image to enhance the
clarity and fidelity of the image details. Furthermore, we present feature
enhancers via a residual dense architecture to eliminate redundant features of
the dehazing process and further alleviate the domain deviation problem.
Extensive experiments on benchmark datasets show that our method reaches the
state-of-the-art. This project code will be available at
\url{https://github.com/Fan-pixel/DCM-dehaze. |
---|---|
DOI: | 10.48550/arxiv.2407.10226 |