Cargando…
Photo-Realistic Image Dehazing and Verifying Networks via Complementary Adversarial Learning
Physical model-based dehazing methods cannot, in general, avoid environmental variables and undesired artifacts such as non-collected illuminance, halo and saturation since it is difficult to accurately estimate the amount of the illuminance, light transmission and airlight. Furthermore, the haze mo...
Autores principales: | Shin, Joongchol, Paik, Joonki |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8471053/ https://www.ncbi.nlm.nih.gov/pubmed/34577388 http://dx.doi.org/10.3390/s21186182 |
Ejemplares similares
-
Gated Dehazing Network via Least Square Adversarial Learning
por: Ha, Eunjae, et al.
Publicado: (2020) -
Remote Sensing Image Dehazing through an Unsupervised Generative Adversarial Network
por: Zhao, Liquan, et al.
Publicado: (2023) -
Deep Binary Classification via Multi-Resolution Network and Stochastic Orthogonality for Subcompact Vehicle Recognition
por: Shin, Joongchol, et al.
Publicado: (2020) -
Wavelength-Adaptive Dehazing Using Histogram Merging-Based Classification for UAV Images
por: Yoon, Inhye, et al.
Publicado: (2015) -
An Adversarial Dual-Branch Network for Nonhomogeneous Dehazing in Tunnel Construction
por: Shi, Zilu, et al.
Publicado: (2023)