A Novel Residual Dense Pyramid Network for Image Dehazing

Abstract

Recently, convolutional neural network (CNN) based on the encoder-decoder structurehave been successfully applied to image dehazing. However, these CNN based dehazing methodshave two limitations: First, these dehazing models are large in size with enormous parameters, whichnot only consumes much GPU memory, but also is hard to train from scratch. Second, these models,which ignore the structural information at different resolutions of intermediate layers, cannot captureinformative texture and edge information for dehazing by stacking more layers. In this paper, wepropose a light-weight end-to-end network named the residual dense pyramid network (RDPN)to address the above problems. To exploit the structural information at different resolutions ofintermediate layers fully, a new residual dense pyramid (RDP) is proposed as a building block.By introducing a dense information fusion layer and the residual learning module, the RDP canmaximize the information flow and extract local features. Furthermore, the RDP further learnsthe structural information from intermediate layers via a multiscale pyramid fusion mechanism.To reduce the number of network parameters and to ease the training process, we use one RDPin the encoder and two RDPs in the decoder, following a multilevel pyramid pooling layer forincorporating global context features before estimating the final result. The extensive experimentalresults on a synthetic dataset and real-world images demonstrate that the new RDPN achievesfavourable performance compared with some state-of-the-art methods, e.g., the recent denselyconnected pyramid dehazing network, the all-in-one dehazing network, the enhanced pix2pixdehazing network, pixel-based alpha blending, artificial multi-exposure image fusions and thegenetic programming estimator, in terms of accuracy, run time and number of parameters. To bespecific, RDPN outperforms all of the above methods in terms of PSNR by at least 4.25 dB. The runtime of the proposed method is 0.021 s, and the number of parameters is 1,534,799, only 6% of thatused by the densely connected pyramid dehazing network.

Advanced Driving Assistance Based on the Fusion of Infrared and Visible Images

“…In the infrared and visible images fusion, many methods have been proposed in the past few years, and they can be divided into six categories according to corresponding schemes, including pyramid methods [ 5 , 6 ], neural network-based methods [ 7 ], wavelet transformation based methods [ 8 ], sparse representation methods [ 9 , 10 ], salient feature methods [ 11 , 12 ], and other methods [ 13 ]. There are three main parts in these fusion methods, i.e., (i) domain transform, (ii) activity level measurement, and (iii) fusion rule design.…”

City-Scale Distance Sensing via Bispectral Light Extinction in Bad Weather

“…This phenomena, severe especially in bad weather, would violate the basic assumption of standard vision that air is transparent. Generally regarded as the hindrance, the computational photography community has made much effort in removing rain and fog [1][2][3][4][5][6]. Just like every cloud has a silver lining, some seminar progress [1,7] instead analysed the visual effects of bad weather to encode the scene structure, such as depth.…”