Combining Stereo and Atmospheric Veil Depth Cues for 3D Reconstruction

Caraffa, Laurent; Tarel, Jean-Philippe

doi:10.2197/ipsjtcva.6.1

Cited by 7 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FRIDA 3 [4] contains 66 foggy outdoor road scenes, which is synthetically generated clear/hazy pairs of stereo images (Caraffa and Tarel 2012). Note that [16] adapted the model on the FRIDA 3 dataset, our approach adapted with the same settings is reported for FRIDA 3 which achieves the best performance.…”

Section: Outdoor Datasetmentioning

confidence: 99%

Progressive Depth Learning for Single Image Dehazing

Liang,

Wang,

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

The formulation of the hazy image is mainly dominated by the reflected lights and ambient airlight. Existing dehazing methods often ignore the depth cues and fail in distant areas where heavier haze disturbs the visibility. However, we note that the guidance of the depth information for transmission estimation could remedy the decreased visibility as distances increase. In turn, the good transmission estimation could facilitate the depth estimation for hazy images. In this paper, a deep end-to-end model that iteratively estimates image depths and transmission maps is proposed to perform an effective depth prediction for hazy images and improve the dehazing performance with the guidance of depth information. The image depth and transmission map are progressively refined to better restore the dehazed image. Our approach benefits from explicitly modeling the inner relationship of image depth and transmission map, which is especially effective for distant hazy areas. Extensive results on the benchmarks demonstrate that our proposed network performs favorably against the state-of-the-art dehazing methods in terms of depth estimation and haze removal.

show abstract

Section: Outdoor Datasetmentioning

confidence: 99%

Progressive Depth Learning for Single Image Dehazing

Liang,

Wang,

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Normally, special features of droplets water into air with maximum concentration introduced the fog. The droplets are scattered due to focused light and create the dense of white background that is known as atmospheric veil [8][9]. The analysis of image processing in foggy image sector is observed especially for image defogging.…”

Section: Fig 1 Detection and Characteristics Of Fogmentioning

confidence: 99%

Persistent exersize on foggy image

Soni¹,

Garg²

2015

2015 International Conference on Futuristic Trends on Computational Analysis and Knowledge Management (ABLAZE)

View full text Add to dashboard Cite

Image processing is the ongoing era of research from last three decades. Most of the industry and researcher are doing the analytical study to understand the basic concept and building the projects for future reference. It means the literature and fundamental is necessary before to deployment a new project. Identical of object and removing the noise for betterment of image is more appropriate terms used in image processing. The fog is also type of noise change the quality of vision. In this paper the authors have focused on fog and techniques adopt to remove the fog. The effect of fog on our society is focused. Matlab simulator is used to analyze the processing of images according to visibility stage.

show abstract

“…However, prior based methods are not suitable for all images; consequently scholars have increasingly focused on to how to improve the universality of dehazing approaches by learning from a database. For instance, Caraffa and Tarel [17] trained a local dictionary from the FRIDA database and used it to converge the final transmission map. By revealing that a synthetic database can be highly similar to real scene features, Tang et al [18] improved the accuracy of the transmission map by combining multiple colour features with random forests.…”

Section: Introductionmentioning

confidence: 99%

Haze Removal Using Aggregated Resolution Convolution Network

Bai

2019

IEEE Access

View full text Add to dashboard Cite

The haze removal technique refers to the process of reconstructing haze-free images from scenes of inclement weather conditions. This task has an extensive demand in practical applications. At present, models based on deep convolution neural networks have made significant progress in the haze removal field, greatly outperforming the traditional prior and constraint methods. However, the current CNNs methods, which involve only a single input image, do not provide sufficient features to determine the optimal transmission maps for haze removal; therefore, we propose and design an aggregated resolution convolution network (ARCN) that uses multiple inputs and aggregates features from a CNN model and the adversarial loss algorithm. Experiments comparing the visual results of our network with those of several previous methods reveal substantial improvements. INDEX TERMSHaze removal, single image dehazing, deep convolutional neural network.

show abstract

Combining Stereo and Atmospheric Veil Depth Cues for 3D Reconstruction

Cited by 7 publications

References 15 publications

Progressive Depth Learning for Single Image Dehazing

Progressive Depth Learning for Single Image Dehazing

Persistent exersize on foggy image

Haze Removal Using Aggregated Resolution Convolution Network

Contact Info

Product

Resources

About