.png){kind=icon}
Return
Diffusion Models Based Null-Space Learning for Remote Sensing Image Dehazing
.png){kind=icon}
PRE
AI
DOI：10.1109/LGRS.2024.3370595.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Remote sensing (RS) dehazing is a challenge topic, as images captured under hazy scenarios often suffer from seriously quality degradation and inconsistency. RS image restoration has been significantly improved with the use of learning-based ways, while current methods are still struggling to restore the complex details for large irregular RS images with ununiform haze. In this letter, we propose an adaptive diffusion null-space dehazing network (ADND-Net), which is a novel diffusion-model-based null-space (NULL) learning toward free-form RS image dehazing. Specifically, a range-null-space decomposition is applied to improve the reverse diffusion process for image consistence. With the help of range-null-space content, we further advance the adaptive region-based diffusion (RD) module to address the unlimited-size RS images and increase the dehazed image quality. Extensive experiments show that our designed model outperforms other comparing dehazing methods on both synthetic and real-world RS datasets.
Keywords:
Cyclic shift
diffusion model
Gaussian noise
range-null-space decomposition
region-based
Journal
IF:
16.4
Papers:
1.0W
Citations:
5.1K
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
ShareSave
ShareSaveShareSaveShareSave
View more