Benchmarking Single-Image Dehazing and Beyond

We present a comprehensive study and evaluation of existing single-image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single-Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics to no-reference metrics and to subjective evaluation, and the novel task-driven evaluation. Experiments on RESIDE shed light on the comparisons and limitations of the state-of-the-art dehazing algorithms, and suggest promising future directions.

[1]  Yang Li,et al.  Improved Techniques for Learning to Dehaze and Beyond: A Collective Study , 2018, ArXiv.

[2]  R. A. Bradley,et al.  RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS THE METHOD OF PAIRED COMPARISONS , 1952 .

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

[4]  Alan C. Bovik,et al.  No-Reference Image Quality Assessment in the Spatial Domain , 2012, IEEE Transactions on Image Processing.

[5]  Jean-Philippe Tarel,et al.  Fast visibility restoration from a single color or gray level image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[6]  Deepa Nair,et al.  An Effective Surround Filter for Image Dehazing , 2014, ICONIAAC '14.

[7]  Jiebo Luo,et al.  Using user generated online photos to estimate and monitor air pollution in major cities , 2015, ICIMCS '15.

[8]  Dengyin Zhang,et al.  Single image haze removal based on the improved atmospheric scattering model , 2017, Neurocomputing.

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

[10]  Thomas S. Huang,et al.  DeepFont: Identify Your Font from An Image , 2015, ACM Multimedia.

[11]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[13]  Xiaochun Cao,et al.  Single Image Dehazing via Multi-scale Convolutional Neural Networks , 2016, ECCV.

[14]  Ian D. Reid,et al.  Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[16]  Sertac Karaman,et al.  Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[17]  Zhu Li,et al.  Robust emotion recognition from low quality and low bit rate video: A deep learning approach , 2017, 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII).

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

[19]  Zhou Wang,et al.  Perceptual evaluation of single image dehazing algorithms , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[20]  Xianming Liu,et al.  When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach , 2017, IJCAI.

[21]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Ko Nishino,et al.  Factorizing Scene Albedo and Depth from a Single Foggy Image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[23]  Yonghong Tian,et al.  Quality Assessment for Comparing Image Enhancement Algorithms , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Robby T. Tan,et al.  Visibility in bad weather from a single image , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Minh N. Do,et al.  Robust Image and Video Dehazing with Visual Artifact Suppression via Gradient Residual Minimization , 2016, ECCV.

[26]  Shree K. Nayar,et al.  Chromatic framework for vision in bad weather , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[27]  F. Zhou,et al.  Single image dehazing motivated by Retinex theory , 2013, 2013 2nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation (IMSNA).

[28]  Thomas S. Huang,et al.  Learning Super-Resolution Jointly From External and Internal Examples , 2015, IEEE Transactions on Image Processing.

[29]  Yoav Y. Schechner,et al.  Polarization: Beneficial for visibility enhancement? , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Dani Lischinski,et al.  Deep photo: model-based photograph enhancement and viewing , 2008, SIGGRAPH Asia '08.

[31]  Gaofeng Meng,et al.  Efficient Image Dehazing with Boundary Constraint and Contextual Regularization , 2013, 2013 IEEE International Conference on Computer Vision.

[32]  Nick Barnes,et al.  Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[33]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Changming Sun,et al.  Image dehazing using adaptive bi-channel priors on superpixels , 2017, Comput. Vis. Image Underst..

[35]  Eirikur Agustsson,et al.  NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[36]  Richard Szeliski,et al.  High-accuracy stereo depth maps using structured light , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[37]  Danping Zou,et al.  Simultaneous video defogging and stereo reconstruction , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Jean-Philippe Tarel,et al.  Vision Enhancement in Homogeneous and Heterogeneous Fog , 2012, IEEE Intelligent Transportation Systems Magazine.

[39]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Shree K. Nayar,et al.  Contrast Restoration of Weather Degraded Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[41]  Christophe Charrier,et al.  Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain , 2012, IEEE Transactions on Image Processing.

[42]  Jing Zhang,et al.  Fast Haze Removal for Nighttime Image Using Maximum Reflectance Prior , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[44]  Luc Van Gool,et al.  Semantic Foggy Scene Understanding with Synthetic Data , 2017, International Journal of Computer Vision.

[45]  Hua Huang,et al.  No-reference image quality assessment based on spatial and spectral entropies , 2014, Signal Process. Image Commun..

[46]  ZissermanAndrew,et al.  The Pascal Visual Object Classes Challenge , 2015 .

[47]  Chih-Yuan Yang,et al.  Single-Image Super-Resolution: A Benchmark , 2014, ECCV.

[48]  Ling Shao,et al.  A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior , 2015, IEEE Transactions on Image Processing.

[49]  Dong Liu,et al.  Recognizable or Not: Towards Image Semantic Quality Assessment for Compression , 2017 .

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

[51]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

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

[53]  Raanan Fattal,et al.  Dehazing Using Color-Lines , 2014, ACM Trans. Graph..

[54]  Alan C. Bovik,et al.  A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms , 2006, IEEE Transactions on Image Processing.

[55]  Ruigang Yang,et al.  Stereoscopic inpainting: Joint color and depth completion from stereo images , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[56]  Ko Nishino,et al.  Bayesian Defogging , 2012, International Journal of Computer Vision.

[57]  Gaurav Sharma,et al.  HazeRD: An outdoor scene dataset and benchmark for single image dehazing , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[58]  Shree K. Nayar,et al.  Instant dehazing of images using polarization , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[59]  Raanan Fattal,et al.  Single image dehazing , 2008, ACM Trans. Graph..

[60]  Luc Van Gool,et al.  The 2005 PASCAL Visual Object Classes Challenge , 2005, MLCW.

[61]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[62]  Xianming Liu,et al.  Robust Video Super-Resolution with Learned Temporal Dynamics , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[63]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[64]  Urho Pulkkinen,et al.  Bayesian analysis of consistent paired comparisons , 1994 .

[65]  Thomas S. Huang,et al.  Studying Very Low Resolution Recognition Using Deep Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[67]  Ketan Tang,et al.  Investigating Haze-Relevant Features in a Learning Framework for Image Dehazing , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[68]  Narendra Ahuja,et al.  A Comparative Study for Single Image Blind Deblurring , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[69]  Xianming Liu,et al.  Learning Temporal Dynamics for Video Super-Resolution: A Deep Learning Approach , 2018, IEEE Transactions on Image Processing.

[70]  Jizheng Xu,et al.  End-to-End United Video Dehazing and Detection , 2017, AAAI.

[71]  Tomas Pfister,et al.  Learning from Simulated and Unsupervised Images through Adversarial Training , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[72]  Michael S. Brown,et al.  Nighttime Haze Removal with Glow and Multiple Light Colors , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).