Saved in:
Bibliographic Details
Main Authors: Yinglong, Wang, Bin, He
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.08510
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913498903085056
author Yinglong, Wang
Bin, He
author_facet Yinglong, Wang
Bin, He
contents Image dehazing aims to restore image clarity and visual quality by reducing atmospheric scattering and absorption effects. While deep learning has made significant strides in this area, more and more methods are constrained by network depth. Consequently, lots of approaches have adopted parallel branching strategies. however, they often prioritize aspects such as resolution, receptive field, or frequency domain segmentation without dynamically partitioning branches based on the distribution of input features. Inspired by dynamic filtering, we propose using cascaded dynamic filters to create a multi-branch network by dynamically generating filter kernels based on feature map distribution. To better handle branch features, we propose a residual multiscale block (RMB), combining different receptive fields. Furthermore, we also introduce a dynamic convolution-based local fusion method to merge features from adjacent branches. Experiments on RESIDE, Haze4K, and O-Haze datasets validate our method's effectiveness, with our model achieving a PSNR of 43.21dB on the RESIDE-Indoor dataset. The code is available at https://github.com/dauing/CasDyF-Net.
format Preprint
id arxiv_https___arxiv_org_abs_2409_08510
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CasDyF-Net: Image Dehazing via Cascaded Dynamic Filters
Yinglong, Wang
Bin, He
Computer Vision and Pattern Recognition
Image dehazing aims to restore image clarity and visual quality by reducing atmospheric scattering and absorption effects. While deep learning has made significant strides in this area, more and more methods are constrained by network depth. Consequently, lots of approaches have adopted parallel branching strategies. however, they often prioritize aspects such as resolution, receptive field, or frequency domain segmentation without dynamically partitioning branches based on the distribution of input features. Inspired by dynamic filtering, we propose using cascaded dynamic filters to create a multi-branch network by dynamically generating filter kernels based on feature map distribution. To better handle branch features, we propose a residual multiscale block (RMB), combining different receptive fields. Furthermore, we also introduce a dynamic convolution-based local fusion method to merge features from adjacent branches. Experiments on RESIDE, Haze4K, and O-Haze datasets validate our method's effectiveness, with our model achieving a PSNR of 43.21dB on the RESIDE-Indoor dataset. The code is available at https://github.com/dauing/CasDyF-Net.
title CasDyF-Net: Image Dehazing via Cascaded Dynamic Filters
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.08510