Unsupervised Neural Rendering for Image Hazing

• Published in: IEEE transactions on image processing Vol. 31; pp. 3987 - 3996
• Main Authors: Li, Boyun, Lin, Yijie, Bai, Jinfeng, Hu, Peng, Lv, Jiancheng, Peng, Xi
• Format: Journal Article
• Language: English
• Published: United States IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Atmospheric modeling; Estimation; Haze; Hazing; Image filters; image hazing; Image transmission; Manuals; Mathematical models; Neural networks; Neural Networks, Computer; prior; Rendering; Rendering (computer graphics); Scattering; Three-dimensional displays; Unsupervised
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2022.3177321

Image hazing aims to render a hazy image from a given clean one, which could be applied to a variety of practical applications such as gaming, filming, photographic filtering, and image dehazing. To generate plausible haze, we study two less-touched but challenging problems in hazy image rendering, namely, i) how to estimate the transmission map from a single image without auxiliary information, and ii) how to adaptively learn the airlight from exemplars, i.e. , unpaired real hazy images. To this end, we propose a neural rendering method for image hazing, dubbed as HazeGEN. To be specific, HazeGEN is a knowledge-driven neural network which estimates the transmission map by leveraging a new prior, i.e. , there exists the structure similarity ( e.g. , contour and luminance) between the transmission map and the input clean image. To adaptively learn the airlight, we build a neural module based on another new prior, i.e. , the rendered hazy image and the exemplar are similar in the airlight distribution. To the best of our knowledge, this could be the first attempt to deeply render hazy images in an unsupervised fashion. Compared with existing haze generation methods, HazeGEN renders the hazy images in an unsupervised, learnable, and controllable manner, thus avoiding the labor-intensive efforts in paired data collection and the domain-shift issue in haze generation. Extensive experiments show the promising performance of our method comparing with some baselines in both qualitative and quantitative comparisons. The code is available at https://github.com/XLearning-SCU .