Abstract | ||
---|---|---|
In this paper, we propose a novel learning-based approach for single image dehazing. The proposed approach is mostly inspired by the observation that the color of the objects fades gradually along with the increment of the scene depth. We regard the RGB values of the pixels within the image as the important feature, and use the back propagation neural network to mine the internal link between color and depth from the training samples, which consists of the hazy images and their corresponding ground truth depth map. With the trained neural network, we can easily restore the depth information as well as the scene radiance from the hazy image. Experimental results show that the proposed approach is able to produce a high-quality haze-free image with the single hazy image and achieve the real-time requirement. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ROBIO.2014.7090535 | ROBIO |
Keywords | Field | DocType |
single image dehazing,haze-free image,backpropagation,scene radiance,back propagation neural network dehazing,image enhancement,neural nets,learning,hazy images,mathematical model,atmospheric modeling,image restoration | Computer vision,Ground truth,Pixel,RGB color model,Artificial intelligence,Image restoration,Depth map,Engineering,Artificial neural network,Internal link,Radiance | Conference |
Citations | PageRank | References |
0 | 0.34 | 20 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiaming Mai | 1 | 1 | 1.37 |
Qingsong Zhu | 2 | 116 | 13.96 |
Di Wu | 3 | 636 | 117.73 |
Yaoqin Xie | 4 | 125 | 21.70 |
Lei Wang | 5 | 25 | 2.48 |