Dense `123' Color Enhancement
Dehazing Network

Runner-Up of NTIRE 2019 Dehazing Challenge

A CVPR Workshop

ABSTRACT

Single image dehazing has gained much attention recently. A typical learning based approach uses example hazy and clean image pairs to train a mapping between the two. Of the learning based methods, those based on deep neural networks have shown to deliver state of the art performance. An important aspect of recovered image quality is the color information, which is severely compromised when the image is corrupted by very dense haze. While many different network architectures have been developed for recovering dehazed images, an explicit attention to recovering individual color channels with a design that ensures their quality has been missing. Our proposed work, focuses on this issue by developing a novel network structure that comprises of: a common DenseNet based feature encoder whose output branches into three distinct DensetNet based decoders to yield estimates of the R, G and B color channels of the image. A subsequent refinement block further enhances the final synthesized RGB/color image by joint processing of these color channels. Inspired by its structure, we call our approach the One-To-Three Color Enhancement Dehazing (123-CEDH) network. To ensure the recovery of physically meaningful and high quality color channels, the main network loss function is further regularized by a multi-scale structural similarity index term as well as a term that enhances color contrast. Experiments reveal that 123-CEDH has the ability to recover color information at early training stages (i.e. in the first few epochs) vs. other highly competitive methods. Validation on the benchmark datasets of the NTIRE'19 and NTIRE'18 dehazing challenges reveals the 123-CEDH to be one of the most competitive -- in the Top 3 methods based on PSNR/SSIM metrics released in the NTIRE'19 competition.

Code

The python version of 123-CEDH testing code can be found at [GitHub].

The Matlab version of post-processing (IRCNN) code can be found at [GitHub].

Network Structure

Dehaze Results

Evaluations

Related Publications

  1. T. Guo, V. Cherukuri, and V. Monga, “Dense `123' Color Enhancement Dehazing Network”, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019. [PDF]

  2. Co-author of C. O. Ancuti, C. Ancuti, R. Timofte et al., “NTIRE 2019 Challenge on image dehazing: Methods and results”, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019. [CVF]

Selected References

  1. C. O. Ancuti et al., “Dense haze: A benchmark for image dehazing with dense-haze and haze-free images,” arXiv preprint arXiv:1904.02904, 2019.

  2. H. Zhang and V. M. Patel, “Densely connected pyramid dehazing network,” in Proc. IEEE Conf. on Comp. Vis. Patt. Recog., 2018, pp. 3194–3203.

  3. H. Zhang, V. Sindagi, and V. M. Patel, “Multi-scale single image dehazing using perceptual pyramid deep network,” in Proc. IEEE Conf. Workshop on Comp. Vis. Patt. Recog., 2018, pp. 902–911.

  4. C. O. Ancuti et al., “Color transfer for underwater dehazing and depth estimation,” in Proc. IEEE Conf. on Image Proc., 2017, pp. 695–699.

Email
ipal.psu@gmail.com

Address
104 Electrical Engineering East,
University Park, PA 16802, USA

Lab Phone:
814-863-7810
814-867-4564