TY  - CONF
AU  - Angel Sappa
AU  - Patricia Suarez
AU  - Henry Velesaca
AU  - Dario Carpio
A2  - CGVCVIP
PY  - 2022//
TI  - Domain Adaptation in Image Dehazing: Exploring the Usage of Images from Virtual Scenarios
BT  - 16th International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing
SP  - 85
EP  - 92
KW  - Domain adaptation
KW  - Synthetic hazed dataset
KW  - Dehazing
N2  - This work presents a novel domain adaptation strategy for deep learning-based approaches to solve the image dehazing problem. Firstly, a large set of synthetic images is generated by using a realistic 3D graphic simulator; these synthetic images contain different densities of haze, which are used for training the model that is later adapted to any real scenario.The adaptation process requires just a few images to fine-tune the model parameters. The proposed strategy allows overcoming the limitation of training a given model with few images. In other words, the proposed strategy implements the adaptation of a haze removal model trained with synthetic images to real scenarios. It should be noticed that it is quite difficult, if not impossible, to have large sets of pairs of real-world images (with and without haze) to train in a supervised way dehazing algorithms. Experimental results are provided showing the validity of the proposed domain adaptation strategy.
UR  - https://www.iadisportal.org/digital-library/iadis-international-conference-big-data-analytics-data-mining-and-computational-intelligence-2022-part-of-mccsis-2022
L1  - http://158.109.8.37/files/SSV2022.pdf
N1  - MSIAU; no proj
ID  - Angel Sappa2022
ER  -