Infrared Image Colorization Using a S-Shape Network

Dong, Ziyue; Kamata, Sei‐ichiro; Breckon, Toby P.

doi:10.1109/icip.2018.8451230

Cited by 31 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [28] a CNN is used with a more sophisticated objective function in order to tackle misalignment issues between the two visible and thermal modalities. In [29] instead an encoder-decoder architecture is applied for performing colorization.…”

Section: B Spectrum Transfer Between Visible and Thermalmentioning

confidence: 99%

Robust pedestrian detection in thermal imagery using synthesized images

Kieu

Berlincioni

Galteri

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

In this paper we propose a method for improving pedestrian detection in the thermal domain using two stages: first, a generative data augmentation approach is used, then a domain adaptation method using generated data adapts an RGB pedestrian detector. Our model, based on the Least-Squares Generative Adversarial Network, is trained to synthesize realistic thermal versions of input RGB images which are then used to augment the limited amount of labeled thermal pedestrian images available for training. We apply our generative data augmentation strategy in order to adapt a pretrained YOLOv3 pedestrian detector to detection in the thermal-only domain. Experimental results demonstrate the effectiveness of our approach: using less than 50% of available real thermal training data, and relying on synthesized data generated by our model in the domain adaptation phase, our detector achieves state-of-the-art results on the KAIST Multispectral Pedestrian Detection Benchmark; even if more real thermal data is available adding GAN generated images to the training data results in improved performance, thus showing that these images act as an effective form of data augmentation. To the best of our knowledge, our detector achieves the best single-modality detection results on KAIST with respect to the state-of-the-art.

show abstract

Section: B Spectrum Transfer Between Visible and Thermalmentioning

confidence: 99%

Robust pedestrian detection in thermal imagery using synthesized images

Kieu

Berlincioni

Galteri

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

show abstract

“…These differences break the pixel-wise consistency in textures between two domains. Up to the present, there are several researches to deal with the NIR colorization problem [29], [30]. Dong et al [30] proposed an end-to-end network for NIR colorization based on UNet.…”

Section: A Related Workmentioning

confidence: 99%

“…Up to the present, there are several researches to deal with the NIR colorization problem [29], [30]. Dong et al [30] proposed an end-to-end network for NIR colorization based on UNet. Suarez et al [31] proposed a triplet deep convolutional GAN (DCGAN) model [32] and improved its colorization performance by the validation on training loss [33].…”

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

NIR to RGB Domain Translation Using Asymmetric Cycle Generative Adversarial Networks

Sun

Jung

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Near infrared (NIR) images have clear textures but do not contain color. In this paper, we propose NIR to RGB domain translation using asymmetric cycle generative adversarial networks (ACGANs). The RGB image (3 channels) has richer information than the NIR image (1 channel), which makes NIR-RGB domain translation asymmetric in information. We adopt asymmetric cycle GANs that have different network capacities according to the translation direction. We combine UNet and ResNet in generator and use the feature pyramid networks (FPNs) in discriminator. With the help of a 128 × 128 large receptive field, we capture rich spatial context information with a multiscale architecture. Experimental results show that the proposed method achieves natural looking NIR colorization results with high generalization ability, i.e. feasible in category unaware cases, and outperforms state-of-the-art ones in realistic colorization and resistance to unregistration.

show abstract

“…DGNN has also attracted significant attention within image-to-image (I2I) translation [8] [20] [19] [44]. I2I translation is a computer vision task to model the mapping between different visual domains, such as style transfer [8], [5], super-resolution [23], photorealistic image synthesis [2], and domain adaptation [26]. For style transfer, a style transfer network [8] was proposed as the DNN that is trained to transfer the style from one image to another while preserving its semantic content.…”

Section: Introductionmentioning

confidence: 99%

UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models

Sasaki,

Willcocks,

Breckon

2021

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a novel unpaired image-to-image translation method that uses denoising diffusion probabilistic models without requiring adversarial training.Our method, UNpaired Image Translation with Denoising Diffusion Probabilistic Models (UNIT-DDPM), trains a generative model to infer the joint distribution of images over both domains as a Markov chain by minimising a denoising score matching objective conditioned on the other domain.In particular, we update both domain translation models simultaneously, and we generate target domain images by a denoising Markov Chain Monte Carlo approach that is conditioned on the input source domain images, based on Langevin dynamics. Our approach provides stable model training for image-to-image translation and generates high-quality image outputs. This enables state-of-the-art Fréchet Inception Distance (FID) performance on several public datasets, including both colour and multispectral imagery, significantly outperforming the contemporary adversarial image-to-image translation methods.

show abstract

Infrared Image Colorization Using a S-Shape Network

Cited by 31 publications

References 11 publications

Robust pedestrian detection in thermal imagery using synthesized images

Robust pedestrian detection in thermal imagery using synthesized images

NIR to RGB Domain Translation Using Asymmetric Cycle Generative Adversarial Networks

UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models

Contact Info

Product

Resources

About