NIR to RGB Domain Translation Using Asymmetric Cycle Generative Adversarial Networks

Sun, Ting; Jung, Cheolkon; Fu, Qingtao; Han, Qihui

doi:10.1109/access.2019.2933671

Cited by 32 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This end-to-end architecture can process images without resolution requirements. The existing database with large scene classification is employed as the training dataset, and the classification label of the dataset is exploited to learn global priors more discriminatively.Tian Sunet al [27] proposed a technology to realize the cross-domain conversion from NIR to RGB through asymmetric periodic generation countermeasures network (ACGAN). In this work, they solved the problem of converting NIR to RGB fields and producing reasonable RGB images from NIR images.…”

Section: B Deep Network-based Methodsmentioning

confidence: 99%

From Coarse to Fine (FC2F): A New Scheme of Colorizing Thermal Infrared Images

et al. 2020

View full text Add to dashboard Cite

Colorization of the thermal infrared image is an unsolved problem because usually there is no one-to-one relationship between an object's color and its temperature. In this paper, we propose a new colorization scheme to address this problem. We first create a coarse colorization image that maintains cross-correlation between its RGB channels. Then the matrix of shift, rotation, and scaling between the coarse colorization image and a source natural color image is constructed. Finally, the transformations act on the coarse colorization image to obtain the resultant image, which has the appearance of the source image. Experiments demonstrate the effectiveness of the new scheme and show its superiority to other state-of-theart methods. The new scheme can be easily extended to the colorization of low illumination images and near-infrared images.

show abstract

Section: B Deep Network-based Methodsmentioning

confidence: 99%

From Coarse to Fine (FC2F): A New Scheme of Colorizing Thermal Infrared Images

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In the past few years, few researchers have done image translation between the visible and IR domain, including near-infrared (NIR) to visible [27][28][29][30], MWIR to grey-scale [31], LWIR to RGB [32,33], and visible to IR [34]. Some general GAN network such as Pix2Pix GAN [19,33,35] was also customized for RGB to IR image generation and for generating infrared textures from visible images [36].…”

Section: Image Conversion Between Visible and Ir Domainsmentioning

confidence: 99%

Converting Optical Videos to Infrared Videos Using Attention GAN and Its Impact on Target Detection and Classification Performance

et al. 2021

View full text Add to dashboard Cite

To apply powerful deep-learning-based algorithms for object detection and classification in infrared videos, it is necessary to have more training data in order to build high-performance models. However, in many surveillance applications, one can have a lot more optical videos than infrared videos. This lack of IR video datasets can be mitigated if optical-to-infrared video conversion is possible. In this paper, we present a new approach for converting optical videos to infrared videos using deep learning. The basic idea is to focus on target areas using attention generative adversarial network (attention GAN), which will preserve the fidelity of target areas. The approach does not require paired images. The performance of the proposed attention GAN has been demonstrated using objective and subjective evaluations. Most importantly, the impact of attention GAN has been demonstrated in improved target detection and classification performance using real-infrared videos.

show abstract

“…Another issue with translation methods is that in the past, researchers have mainly focused on translation between two domains in the RGB modality. However, recently several researchers have had success with near-infrared (NIR) to RGB translation [29,28,23,18,22,27]. Also, CNN based translation methods help translate IR images to RGB for facial recognition [31,25].…”

Section: Image Translation Networkmentioning

confidence: 99%

Unsupervised object detection via LWIR/RGB translation

Abbott

Robertson

Rincón

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

In this work, we present two new methods to overcome the lack of annotated long-wavelength infrared (LWIR) data by exploiting the abundance of similar RGB imagery. We introduce a novel unsupervised adaptation to the cycleGAN architecture for translating non-corresponding LWIR/RGB datasets. Our ultimate goal is high detection rates in the synthetic RGB/real LWIR imagery using only RGB labelled imagery for training detection algorithms. We translate LWIR imagery to RGB, allowing us to use an RGB trained detection algorithm. We, thereby remove the need for labelled LWIR imagery for training detection algorithms. In addition, we translate RGB to LWIR to fine-tune a network for detection in real LWIR imagery. Experimental results show that our adaption helps to create synthetic RGB imagery with higher detection rates across two different datasets. We also find that combining the synthetic RGB and real LWIR imagery produces higher F1 scores on the RGB trained detection network. Fine-tuning detection networks with synthetic LWIR and testing with real LWIR imagery produce the highest F1 scores.

show abstract

NIR to RGB Domain Translation Using Asymmetric Cycle Generative Adversarial Networks

Cited by 32 publications

References 35 publications

From Coarse to Fine (FC2F): A New Scheme of Colorizing Thermal Infrared Images

From Coarse to Fine (FC2F): A New Scheme of Colorizing Thermal Infrared Images

Converting Optical Videos to Infrared Videos Using Attention GAN and Its Impact on Target Detection and Classification Performance

Unsupervised object detection via LWIR/RGB translation

Contact Info

Product

Resources

About