Near-Infrared Fusion for Photorealistic Image Dehazing

Dümbgen, Frederike; Helou, Majed El; Gucevska, Natalija; Süsstrunk, Sabine

doi:10.2352/issn.2470-1173.2018.16.color-321

Cited by 18 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the computer vision field, multispectral images make up the data in the non-visible light spectrum and help better understand the scene characteristics. For example, Freiburg Forest dataset Apart from semantic segmentation, multi-spectral images are also used in other computer vision tasks, including pedestrian detection [152,153], face recognition [154], image dehazing [155,156], video surveillance [157], to name a few.…”

Section: Near-infrared Datasetsmentioning

confidence: 99%

Deep multimodal fusion for semantic image segmentation: A survey

Zhang

Sidibé

Morel

et al. 2021

Image and Vision Computing

131

View full text Add to dashboard Cite

Recent advances in deep learning have shown excellent performance in various scene understanding tasks. However, in some complex environments or under challenging conditions, it is necessary to employ multiple modalities that provide complementary information on the same scene. A variety of studies have demonstrated that deep multimodal fusion for semantic image segmentation achieves significant performance improvement. These fusion approaches take the benefits of multiple information sources and generate an optimal joint prediction automatically. This paper describes the essential background concepts of deep multimodal fusion and the relevant applications in computer vision. In particular, we provide a systematic survey of multimodal fusion methodologies, multimodal segmentation datasets, and quantitative evaluations on the benchmark datasets. Existing fusion methods are summarized according to a common taxonomy: early fusion, late fusion, and hybrid fusion. Based on their performance, we analyze the strengths and weaknesses of different fusion strategies. Current challenges and design choices are discussed, aiming to provide the reader with a comprehensive and heuristic view of deep multimodal image segmentation.

show abstract

Section: Near-infrared Datasetsmentioning

confidence: 99%

Deep multimodal fusion for semantic image segmentation: A survey

Zhang

Sidibé

Morel

et al. 2021

Image and Vision Computing

131

View full text Add to dashboard Cite

show abstract

“…1. This near haze-free feature of NIR imagery has already been exploited in the past by many researchers [19], [16], [17] for removing haze from RGB image.…”

Section: Introductionmentioning

confidence: 99%

“…To prevent NIR radiation from affecting the color image, most digital cameras place an IR-cut filter in front of the camera sensor. In recent years, the information from NIR imagery has proven very useful in various image processing application [11], [12], [13], especially in image dehazing [14], [15], [16], [17].…”

Section: Introductionmentioning

confidence: 99%

Near-Infrared Depth-Independent Image Dehazing using Haar Wavelets

Laha,

Sharma,

et al. 2022

Preprint

View full text Add to dashboard Cite

We propose a fusion algorithm for haze removal that combines color information from an RGB image and edge information extracted from its corresponding NIR image using Haar wavelets. The proposed algorithm is based on the key observation that NIR edge features are more prominent in the hazy regions of the image than the RGB edge features in those same regions. To combine the color and edge information, we introduce a haze-weight map which proportionately distributes the color and edge information during the fusion process. Because NIR images are, intrinsically, nearly haze-free, our work makes no assumptions like existing works that rely on a scattering model and essentially designing a depth-independent method. This helps in minimizing artifacts and gives a more realistic sense to the restored haze-free image. Extensive experiments show that the proposed algorithm is both qualitatively and quantitatively better on several key metrics when compared to existing state-of-the-art methods.

show abstract

“…In fact, any procedure requiring the analysis of two or more images of the same scene benefits from image fusion [1]. For instance, image fusion between visible and infrared bands [2] is used in night-time surveillance, image dehazing [3], face recognition [4], military reconnaissance missions, and firefighting [5]. In medical imaging applications, images can come from multiple modalities such as magnetic resonance imaging (MRI), positron emission tomography (PET), and computed tomography (CT).…”

Section: Introductionmentioning

confidence: 99%

Fast and Efficient Zero-Learning Image Fusion

Lahoud¹,

Süsstrunk²

2019

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a real-time image fusion method using pre-trained neural networks. Our method generates a single image containing features from multiple sources. We first decompose images into a base layer representing large scale intensity variations, and a detail layer containing small scale changes. We use visual saliency to fuse the base layers, and deep feature maps extracted from a pre-trained neural network to fuse the detail layers. We conduct ablation studies to analyze our method's parameters such as decomposition filters, weight construction methods, and network depth and architecture. Then, we validate its effectiveness and speed on thermal, medical, and multi-focus fusion. We also apply it to multiple image inputs such as multiexposure sequences. The experimental results demonstrate that our technique achieves state-of-the-art performance in visual quality, objective assessment, and runtime efficiency.

show abstract

Near-Infrared Fusion for Photorealistic Image Dehazing

Cited by 18 publications

References 16 publications

Deep multimodal fusion for semantic image segmentation: A survey

Deep multimodal fusion for semantic image segmentation: A survey

Near-Infrared Depth-Independent Image Dehazing using Haar Wavelets

Fast and Efficient Zero-Learning Image Fusion

Contact Info

Product

Resources

About