Sorry, you need to enable JavaScript to visit this website.

SDRNET: SALIENCY-GUIDED DYNAMIC RESTORATION NETWORK FOR RAIN AND HAZE REMOVAL IN NIGHTTIME IMAGES

DOI:
10.60864/0wge-8h87
Citation Author(s):
Submitted by:
Wanning Zhu
Last updated:
6 June 2024 - 10:50am
Document Type:
Poster
 

Due to the different physical imaging models, most haze or rain removal methods for daytime images are not suitable for nighttime images. Fog effect produced by the accumu-lation of rain also brings great challenges to the restoration of lowlight nighttime images. To deal well with the multi-ple noise interference in this complex situation, we propose a saliency-guided dynamic restoration network (SDRNet) that can remove rain and haze in nighttime scenes. First, a saliency-guided detail enhancement preprocessing method is designed to get images with clearer details as the auxilia-ry input. Second, following a rain removal network (RRN), we design an all-in-one nighttime dehazing network (ANDN) to estimate the spatially variable ambient light and transmission comprehensively by deforming the nighttime haze image model. Finally, an attention-based enhancement network (AEN) with dynamic fusion attention module is proposed to enhance the lowlight background image. Experimental results indicate that SDRNet can ob-tain clearer images with less fog and distortion compared with other methods.

up
0 users have voted: