Polarimetric Thermal to Visible Face Verification via Self-Attention Guided Synthesis

Di, Xing; Riggan, Benjamin S.; Hu, Shuowen; Short, Nathaniel J.; Patel, Vishal M.

doi:10.1109/icb45273.2019.8987329

Cited by 33 publications

(22 citation statements)

References 37 publications

(120 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Heterogeneous face recognition (HFR) problem has attracted increasing attention in the recent years (Sarfraz and Stiefelhagen 2015;Riggan et al 2016;Liu et al 2016;Zhang et al 2018;Di et al 2019). NIR-VIS face recognition has been one of the most representative and studied issues in the research field.…”

Section: Heterogeneous Face Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition

Huang

et al. 2021

Int J Comput Vis

View full text Add to dashboard Cite

Near-infrared-visible (NIR-VIS) heterogeneous face recognition matches NIR to corresponding VIS face images. However, due to the sensing gap, NIR images often lose some identity information so that the NIR-VIS recognition issue is more difficult than conventional VIS face recognition. Recently, NIR-VIS heterogeneous face recognition has attracted considerable attention in the computer vision community because of its convenience and adaptability in practical applications. Various deep learning-based methods have been proposed and substantially increased the recognition performance, but the lack of NIR-VIS training samples leads to the difficulty of the model training process. In this paper, we propose a new Large-Scale Multi-Pose High-Quality NIR-VIS database 'LAMP-HQ' containing 56,788 NIR and 16,828 VIS images of 573 subjects with large diversities in pose, illumination, attribute, scene and accessory. We furnish a benchmark along with the protocol for NIR-VIS face recognition via generation on LAMP-HQ, including Pixel2-Pixel, CycleGAN, ADFL, PCFH, and PACH. Furthermore, we propose a novel exemplar-based variational spectral attention network to produce high-fidelity VIS images from NIR data. A spectral conditional attention module is introduced to reduce the domain gap between NIR and VIS data and then improve the performance of NIR-VIS heterogeneous face recognition on various databases including the LAMP-HQ.

show abstract

Section: Heterogeneous Face Recognitionmentioning

confidence: 99%

“…Zhang et al (2019b) employ the GAN model to synthesize visual images from polarimetric thermal domain. A self-attention mechanism is used in (Di et al 2019) to guide the generating of visual images.…”

Section: Heterogeneous Face Recognitionmentioning

confidence: 99%

LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition

Huang

et al. 2021

Int J Comput Vis

View full text Add to dashboard Cite

show abstract

“…Apart from formulating new loss functions, some researchers have designed novel network architectures for the generator such as a densely connected encoder-decoder structure [10], cascaded-in-cascaded blocks [12], and selfattention blocks [3], that enable generating higher quality images. Iranmanesh et al [10] presented a coupled generative adversarial network (CpGAN) architecture that incorporated a densely connected encoder-decoder structure in the generator.…”

Section: Related Workmentioning

confidence: 99%

Explainable Thermal to Visible Face Recognition Using Latent-Guided Generative Adversarial Network

Anghelone

Chen²,

Fauré³

et al. 2021

2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)

View full text Add to dashboard Cite

One of the main challenges in performing thermalto-visible face image translation is preserving the identity across different spectral bands. Existing work does not effectively disentangle the identity from other confounding factors. In this paper, we propose a Latent-Guided Generative Adversarial Network (LG-GAN) to explicitly decompose an input image into identity code that is spectral-invariant and style code that is spectral-dependent. By using such a disentanglement, we are able to analyze the identity preservation by interpreting and visualizing the identity code. We present extensive face recognition experiments on two challenging Visible-Thermal face datasets. We show that the learned identity code is effective in preserving the identity, thus offering useful insights on interpreting and explaining thermal-to-visible face image translation.

show abstract

“…Face recognition as a research problem has been intensively studied to date, although most works have assumed a working spectrum of visible light. To break the limits of face recognition under visible light, some scholars and research teams have turned to face recognition using the infrared (IR) spectrum, which is still a growing research topic [1][2][3][4][5][6][7][8][9][10]. Cross-spectral face recognition between IR and visible light imageries takes us beyond these limits and allows recognition to be performed at nighttime or in harsh environments such as fog, haze, and rain [11,12].…”

Section: Introductionmentioning

confidence: 99%

Balancing Heterogeneous Image Quality for Improved Cross-Spectral Face Recognition

Cao

Cen

Zhao

et al. 2021

Sensors

View full text Add to dashboard Cite

Matching infrared (IR) facial probes against a gallery of visible light faces remains a challenge, especially when combined with cross-distance due to deteriorated quality of the IR data. In this paper, we study the scenario where visible light faces are acquired at a short standoff, while IR faces are long-range data. To address the issue of quality imbalance between the heterogeneous imagery, we propose to compensate it by upgrading the lower-quality IR faces. Specifically, this is realized through cascaded face enhancement that combines an existing denoising algorithm (BM3D) with a new deep-learning-based deblurring model we propose (named SVDFace). Different IR bands, short-wave infrared (SWIR) and near-infrared (NIR), as well as different standoffs, are involved in the experiments. Results show that, in all cases, our proposed approach for quality balancing yields improved recognition performance, which is especially effective when involving SWIR images at a longer standoff. Our approach outperforms another easy and straightforward downgrading approach. The cascaded face enhancement structure is also shown to be beneficial and necessary. Finally, inspired by the singular value decomposition (SVD) theory, the proposed deblurring model of SVDFace is succinct, efficient and interpretable in structure. It is proven to be advantageous over traditional deblurring algorithms as well as state-of-the-art deep-learning-based deblurring algorithms.

show abstract

Polarimetric Thermal to Visible Face Verification via Self-Attention Guided Synthesis

Cited by 33 publications

References 37 publications

LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition

LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition

Explainable Thermal to Visible Face Recognition Using Latent-Guided Generative Adversarial Network

Balancing Heterogeneous Image Quality for Improved Cross-Spectral Face Recognition

Contact Info

Product

Resources

About