arXiv Open Access 2020

Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision

Chen Liu Jiaqi Fan Guosheng Yin

Lihat Sumber

Abstrak

Image dehazing without paired haze-free images is of immense importance, as acquiring paired images often entails significant cost. However, we observe that previous unpaired image dehazing approaches tend to suffer from performance degradation near depth borders, where depth tends to vary abruptly. Hence, we propose to anneal the depth border degradation in unpaired image dehazing with cyclic perceptual-depth supervision. Coupled with the dual-path feature re-using backbones of the generators and discriminators, our model achieves $\mathbf{20.36}$ Peak Signal-to-Noise Ratio (PSNR) on NYU Depth V2 dataset, significantly outperforming its predecessors with reduced Floating Point Operations (FLOPs).

Topik & Kata Kunci

eess.IV cs.CV

Penulis (3)

Chen Liu

Jiaqi Fan

Guosheng Yin

Format Sitasi

APA MLA BibTeX

Liu, C., Fan, J., Yin, G. (2020). Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision. https://arxiv.org/abs/2007.05220

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓