Abstract | ||
---|---|---|
In this work we propose HR-Dehazer a novel and accurate method for image dehazing. An encoder-decoder neural network is trained to learn a direct mapping between a hazy image and its respective clear version. We designed a special loss that forces the network to keep into account the semantics of the input image and to promote consistency among local structures. In addition, this loss makes the system more invariant to scale changes. Quantitative results on the recently released Dense-Haze dataset introduced for the NTIRE2019-Dehazing Challenge demonstrates the effectiveness of the proposed method. Furthermore, qualitative results on real data show that the described solution generalizes well to different never-seen scenarios. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CVPRW.2019.00244 | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
Field | DocType | ISSN |
Computer vision,Architecture,Encoder decoder,Computer science,Artificial intelligence | Conference | 2160-7508 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simone Bianco | 1 | 226 | 24.48 |
Luigi Celona | 2 | 0 | 0.68 |
Flavio Piccoli | 3 | 16 | 2.09 |
Raimondo Schettini | 4 | 1476 | 154.06 |