TY  - CONF
AU  - Patricia Suarez
AU  - Dario Carpio
AU  - Angel Sappa
AU  - Henry Velesaca
A2  - SITIS
PY  - 2022//
TI  - Transformer based Image Dehazing
BT  - 16th IEEE International Conference on Signal Image Technology & Internet Based System
KW  - atmospheric light
KW  - brightness component
KW  - computational cost
KW  - dehazing quality
KW  - haze-free image
N2  - This paper presents a novel approach to remove non homogeneous haze from real images. The proposed method consists mainly of image feature extraction, haze removal, and image reconstruction. To accomplish this challenging task, we propose an architecture based on transformers, which have been recently introduced and have shown great potential in different computer vision tasks. Our model is based on the SwinIR an image restoration architecture based on a transformer, but by modifying the deep feature extraction module, the depth level of the model, and by applying a combined loss function that improves styling and adapts the model for the non-homogeneous haze removal present in images. The obtained results prove to be superior to those obtained by state-of-the-art models.
UR  - 16th IEEE Int. Conf. on Signal Image Technology & Internet Based System
L1  - http://refbase.cvc.uab.es/files/SCS2022.pdf
UR  - http://dx.doi.org/10.1109/SITIS57111.2022.00037
N1  - MSIAU; no proj
ID  - Patricia Suarez2022
ER  -