Semantic Guidance Learning for High-Resolution Non-homogeneous Dehazing
Journal
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Journal Volume
2023-June
ISBN
9798350302493
Date Issued
2023-01-01
Author(s)
Yang, Hao Hsiang
Chen, I. Hsiang
Hsieh, Chia Hsuan
Chang, Hua En
Chiang, Yuan Chun
Chen, Yi Chung
Huang, Zhi Kai
WEI-TING CHEN
Abstract
High-resolution non-homogeneous dehazing aims to generate a clear image from a 4000 × 6000 image with non-homogeneous haze. To the best of our knowledge, this task is a new challenge that was not addressed in the previous literature. To address this issue, we propose semantic-guided loss functions for high-resolution non-homogeneous dehazing. We find semantic information contains strong texture and color prior. Thus, we proposed to adopt the pre-trained model to generate the semantic mask to guide the neural network during the training phase. On the other hand, to handle the non-homogeneous dehazing process in the high-resolution scenario, we adjust the kernel size of the model to increase the receptive field. Furthermore, to deal with the different image sizes during the training and the testing phase, several post-processing methods are applied to improve the high-resolution non-homogeneous dehazing. Several experiments performed on challenging benchmark show that the proposed model achieves competitive performance in the NTIRE 2023 HR NonHomogeneous Dehazing Challenge.
Type
conference paper