FWB-Net: Front White Balance Network for Color Shift Correction in Single Image Dehazing Via Atmospheric Light Estimation

In recent years, single image dehazing deep models based on Atmospheric Scattering Model (ASM) have achieved remarkable results. But the dehazing outputs of those models suffer from color shift. Analyzing the ASM model shows that the atmospheric light factor (ALF) is set as a scalar which indicates ALF is constant for whole image. However, for images taken in real-world, the illumination is not uniformly distributed over whole image which brings model mismatch and possibly results in color shift of the deep models using ASM. Bearing this in mind, in this study, first, a new non-homogeneous atmospheric scattering model (NH-ASM) is proposed for improving image modeling of hazy images taken under complex illumination conditions. Second, a new U-Net based front white balance module (FWB-Module) is dedicatedly designed to correct color shift before generating dehazing result via atmospheric light estimation. Third, a new FWB loss is innovatively developed for training FWB-Module, which imposes penalty on color shift. In the end, based on NH-ASM and front white balance technology, an end-to-end CNN-based color-shift-restraining dehazing network is developed, termed as FWB-Net. Experimental results demonstrate the effectiveness and superiority of our proposed FWB-Net for dehazing on both synthetic and real-world images.

[1]  Dan Margulis Photoshop LAB Color: The Canyon Conundrum and Other Adventures in the Most Powerful Colorspace , 2005 .

[2]  Shai Avidan,et al.  Non-local Image Dehazing , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Radu Timofte,et al.  O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[4]  Jun Chen,et al.  GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[5]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[6]  Djemel Ziou,et al.  Image Quality Metrics: PSNR vs. SSIM , 2010, 2010 20th International Conference on Pattern Recognition.

[7]  Dacheng Tao,et al.  DehazeNet: An End-to-End System for Single Image Haze Removal , 2016, IEEE Transactions on Image Processing.

[8]  Michael S. Brown,et al.  Deep White-Balance Editing , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Michael S. Brown,et al.  Haze Visibility Enhancement: A Survey and Quantitative Benchmarking , 2016, Comput. Vis. Image Underst..

[10]  Wei Liu,et al.  Gated Fusion Network for Single Image Dehazing , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  A. Cantor Optics of the atmosphere--Scattering by molecules and particles , 1978, IEEE Journal of Quantum Electronics.

[12]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[13]  Jean-Yves Audibert Optimization for Machine Learning , 1995 .

[14]  Zehan Chen,et al.  ABC-NET: Avoiding Blocking Effect & Color Shift Network for Single Image Dehazing Via Restraining Transmission Bias , 2020, 2020 IEEE International Conference on Image Processing (ICIP).

[15]  Shree K. Nayar,et al.  Vision and the Atmosphere , 2002, International Journal of Computer Vision.

[16]  C. Ripamonti,et al.  Computational Colour Science Using MATLAB , 2004 .

[17]  Mohinder Malhotra Single Image Haze Removal Using Dark Channel Prior , 2016 .

[18]  Jizheng Xu,et al.  AOD-Net: All-in-One Dehazing Network , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[19]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[20]  Derek Hoiem,et al.  Indoor Segmentation and Support Inference from RGBD Images , 2012, ECCV.