Single image dehazing using the change of detail prior

Deep Dehazing Network With Latent Ensembling Architecture and Adversarial Learning

Most existing dehazing algorithms recover haze-free image by solving the hazy imaging model using estimated transmission map and global atmospheric light. However, inaccurate estimation of these variables and the strong assumptions of imaging model result in unrealistic dehazing results. In this paper, we use the adversarial game between a pair of neural networks to accomplish end-to-end photo-realistic dehazing. To avoid uniform contrast enhancement, the generator learns to simultaneously restore haze-free image and capture the non-uniformity of haze. The modules for the two tasks are assembled in sequential and parallel manners to enable information sharing at different levels, and the architecture of the generator implicitly forms an ensemble of dehazing models that allows for feature selection. A multi-scale discriminator competes with the generator by learning to detect dehazing artifacts and the inconsistency between dehazed image and the spatial variation of haze. Unlike existing works that penalize dehazing artifacts via hand-crafted loss, the proposed algorithm uses the identity mapping in the space of clear-scene images to regularize data-driven dehazing. The proposed work also addresses the adaptability of data-driven dehazing to high-level computer vision task. We propose a task-driven training strategy that can optimize the object detection performance on dehazed images without updating the parameters of object detector. Performance of the proposed algorithm is assessed on the RESIDE, I-Haze, and O-Haze benchmarks. The comparison with ten state-of-the-art algorithms shows that the proposed work is the best performer in most competitions.

Impact of Dehazing on Underwater Marker Detection for Augmented Reality

Underwater augmented reality is a very challenging task and amongst several issues, one of the most crucial aspects involves real-time tracking. Particles present in water combined with the uneven absorption of light decrease the visibility in the underwater environment. Dehazing methods are used in many areas to improve the quality of digital image data that is degraded by the influence of the environment. This paper describes the visibility conditions affecting underwater scenes and shows existing dehazing techniques that successfully improve the quality of underwater images. Four underwater dehazing methods are selected for evaluation of their capability of improving the success of square marker detection in underwater videos. Two reviewed methods represent approaches of image restoration: Multi-Scale Fusion, and Bright Channel Prior. Another two methods evaluated, the Automatic Color Enhancement and the Screened Poisson Equation, are methods of image enhancement. The evaluation uses diverse test data set to evaluate different environmental conditions. Results of the evaluation show an increased number of successful marker detections in videos pre-processed by dehazing algorithms and evaluate the performance of each compared method. The Screened Poisson method performs slightly better to other methods across various tested environments, while Bright Channel Prior and Automatic Color Enhancement shows similarly positive results.