Double Branch Image Dehazing Algorithm Based on Probabilistic Uncertainty Modeling

Addressing the problem that deep learning methods fail to consider the uncertainty inherent in image dehazing results in real-world scenarios, this paper proposes PP-VAENet, a single-modal image dehazing method based on probabilistic uncertainty modeling. The PP-VAENet method innovatively decouples...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2025 8th International Conference on Computer Information Science and Application Technology (CISAT) s. 574 - 578
Hlavní autoři: Zhou, Yuchao, Sun, Hongyu, Dong, Jingwei, Yan, Yinuo, Shao, Luyang
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 11.07.2025
Témata:
Decision making
Deep learning
Feature extraction
Image dehazing
Maximum likelihood estimation
Probabilistic logic
Robustness
Synthetic data
Uncertainty
Uncertainty modeling
Visual effects
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Addressing the problem that deep learning methods fail to consider the uncertainty inherent in image dehazing results in real-world scenarios, this paper proposes PP-VAENet, a single-modal image dehazing method based on probabilistic uncertainty modeling. The PP-VAENet method innovatively decouples the dehazing process into two stages: distribution estimation and consensus decision-making: (1) constructing latent space distributions through Conditional Variational Autoencoder (CVAE), then combining with Probabilistic Adaptive Instance Normalization module (PAdaIN) to generate multiple reasonable candidate dehazed images; (2) finally selecting the optimal dehazed image from candidate results through Maximum Likelihood Estimation. To enhance the network's feature representation capability when constructing distribution estimation, this paper designs the NIN-Mamba module to fuse local feature extraction with global dependency modeling. Comparative experimental results on public datasets demonstrate that PP-VAENet surpasses existing advanced single-modal image dehazing algorithms in both quantitative and qualitative results.
DOI:10.1109/CISAT66811.2025.11181867