Nonuniformly Dehaze Network for Visible Remote Sensing Images

Zhaojie Chen, Qi Li, Huajun Feng, Zhihai Xu, Yueting Chen; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 447-456


Nonuniform haze on remote sensing images degrades image quality and hinders many high-level tasks. In this paper, we propose a Nonuniformly Dehaze Network towards nonuniform haze on visible remote sensing images. To extract robust haze-aware features, we propose Nonuniformly Excite (NE) module. Inspired by the well-known gather-excite attention module, NE module works in a map-excite manner. In the map operation, we utilize a proposed Dual Attention Dehaze block to extract local enhanced features. In the gather operation, we utilize a strided deformable convolution to nonuniformly process features and extract nonlocal haze-aware features. In the excite operation, we employ a pixel-wise attention between local enhanced features and nonlocal haze-aware features, to gain finer haze-aware features. Moreover, we recursively embed NE modules in a multi-scale framework. It helps not only significantly reduce network's parameters, but also recursively deliver and fuse haze-aware features from higher levels, which makes learning more efficient. Experiments demonstrate that the proposed network performs favorably against the state-of-the-art methods on both synthetic and real-world images.

Related Material

@InProceedings{Chen_2022_CVPR, author = {Chen, Zhaojie and Li, Qi and Feng, Huajun and Xu, Zhihai and Chen, Yueting}, title = {Nonuniformly Dehaze Network for Visible Remote Sensing Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {447-456} }