Akira Hirabayashi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Akira Hirabayashi has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Daichi Kitahara
Dept. of Information Science and Engineering, Ritsumeikan University
3 shared publications- Laurent Condat
Visual Computing Center, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia
3 shared publications - Hiroki Kuroda
Department of Information and Management Systems Engineering, Nagaoka University of Technology
2 shared publications - Kazushi Mimura
Faculty of Information Sciences Hiroshima City University 3-4-1 Ozukahigashi Asaminami-ku Hiroshima-shi 731-3194 Hiroshima Japan
2 shared publications Aiko Nishiyama
College of Information Science and Engineering, Ritsumeikan University
1 shared publicationHiroya Yamamoto
Dept. of Information Science and Engineering, Ritsumeikan University
1 shared publication
Latest Publications
- 1 April 2022
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E105.A (4) , 704-718
Image Super-Resolution via Generative Adversarial Networks Using Metric Projections onto Consistent Sets for Low-Resolution Inputs
This paper addresses single image super-resolution (SR) based on convolutional neural networks (CNNs). It is known that recovery of high-frequency components in output SR images of CNNs learned by the least square errors or least absolute errors is insufficient. To generate realistic high-frequency components, SR methods using generative adversarial networks (GANs), composed of one generator and one discriminator, are developed. However, when the generator tries to induce the discriminator's misjudgment, not only realistic high-frequency components but also some artifacts are generated, and objective indices such as PSNR decrease. To reduce the artifacts in the GAN-based SR methods, we consider the set of all SR images whose square errors between downscaling results and the input image are within a certain range, and propose to apply the metric projection onto this consistent set in the output layers of the generators. The proposed technique guarantees the consistency between output SR images and input images, and the generators with the proposed projection can generate high-frequency components with few artifacts while keeping low-frequency ones as appropriate for the known noise level. Numerical experiments show that the proposed technique reduces artifacts included in the original SR images of a GAN-based SR method while generating realistic high-frequency components with better PSNR values in both noise-free and noisy situations. Since the proposed technique can be integrated into various generators if the downscaling process is known, we can give the consistency to existing methods with the input images without degrading other SR performance.
- 1 April 2022
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E105.A (4) , 704-718
Image Super-Resolution via Generative Adversarial Networks Using Metric Projections onto Consistent Sets for Low-Resolution Inputs
This paper addresses single image super-resolution (SR) based on convolutional neural networks (CNNs). It is known that recovery of high-frequency components in output SR images of CNNs learned by the least square errors or least absolute errors is insufficient. To generate realistic high-frequency components, SR methods using generative adversarial networks (GANs), composed of one generator and one discriminator, are developed. However, when the generator tries to induce the discriminator's misjudgment, not only realistic high-frequency components but also some artifacts are generated, and objective indices such as PSNR decrease. To reduce the artifacts in the GAN-based SR methods, we consider the set of all SR images whose square errors between downscaling results and the input image are within a certain range, and propose to apply the metric projection onto this consistent set in the output layers of the generators. The proposed technique guarantees the consistency between output SR images and input images, and the generators with the proposed projection can generate high-frequency components with few artifacts while keeping low-frequency ones as appropriate for the known noise level. Numerical experiments show that the proposed technique reduces artifacts included in the original SR images of a GAN-based SR method while generating realistic high-frequency components with better PSNR values in both noise-free and noisy situations. Since the proposed technique can be integrated into various generators if the downscaling process is known, we can give the consistency to existing methods with the input images without degrading other SR performance.
- 1 January 2021
- Published by Acoustical Society of Japan in Acoustical Science and Technology
- Vol. 42 (6) , 305-313
WaveNet modeling of distortion pedal using spectral features
The present paper proposes a distortion pedal modeling method using the so-called WaveNet. A state-of-the-art method constructs a feedforward network by modifying the original autoregressive WaveNet, and trains it so that a loss function defined by the normalized mean squared error between the high-pass filtered outputs is minimized This method works well for pedals with low distortion, but not for those with high distortion. To solve this problem, the proposed method exploits the same WaveNet, but a novel loss function, which is defined by a weighted sum of errors in time and time-frequency (T-F) domains. The error in the time domain is defined by the mean squared error without the high-pass filtering, while that in the T-F domain is defined by a divergence between spectral features computed from the short-time Fourier transform. Numerical experiments using a pedal with high distortion, the Ibanez SD9, show that the proposed method is capable of precisely reproducing high-frequency components without attenuation of low-frequency components compared to the state-of-the-art method.
- 1 January 2021
- Published by Acoustical Society of Japan in Acoustical Science and Technology
- Vol. 42 (6) , 305-313
WaveNet modeling of distortion pedal using spectral features
The present paper proposes a distortion pedal modeling method using the so-called WaveNet. A state-of-the-art method constructs a feedforward network by modifying the original autoregressive WaveNet, and trains it so that a loss function defined by the normalized mean squared error between the high-pass filtered outputs is minimized This method works well for pedals with low distortion, but not for those with high distortion. To solve this problem, the proposed method exploits the same WaveNet, but a novel loss function, which is defined by a weighted sum of errors in time and time-frequency (T-F) domains. The error in the time domain is defined by the mean squared error without the high-pass filtering, while that in the T-F domain is defined by a divergence between spectral features computed from the short-time Fourier transform. Numerical experiments using a pedal with high distortion, the Ibanez SD9, show that the proposed method is capable of precisely reproducing high-frequency components without attenuation of low-frequency components compared to the state-of-the-art method.
- 1 January 2020
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E104A (4) , 702-713
Multiclass Dictionary-Based Statistical Iterative Reconstruction for Low-Dose CT
This paper proposes a high-quality computed tomography (CT) image reconstruction method from low-dose X-ray projection data. A state-of-the-art method, proposed by Xu et al., exploits dictionary learning for image patches. This method generates an overcomplete dictionary from patches of standard-dose CT images and reconstructs low-dose CT images by minimizing the sum of a data fidelity and a regularization term based on sparse representations with the dictionary. However, this method does not take characteristics of each patch, such as textures or edges, into account. In this paper, we propose to classify all patches into several classes and utilize an individual dictionary with an individual regularization parameter for each class. Furthermore, for fast computation, we introduce the orthogonality to column vectors of each dictionary. Since similar patches are collected in the same cluster, accuracy degradation by the orthogonality hardly occurs. Our simulations show that the proposed method outperforms the state-of-the-art in terms of both accuracy and speed.
- 1 January 2020
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E104A (4) , 702-713
Multiclass Dictionary-Based Statistical Iterative Reconstruction for Low-Dose CT
This paper proposes a high-quality computed tomography (CT) image reconstruction method from low-dose X-ray projection data. A state-of-the-art method, proposed by Xu et al., exploits dictionary learning for image patches. This method generates an overcomplete dictionary from patches of standard-dose CT images and reconstructs low-dose CT images by minimizing the sum of a data fidelity and a regularization term based on sparse representations with the dictionary. However, this method does not take characteristics of each patch, such as textures or edges, into account. In this paper, we propose to classify all patches into several classes and utilize an individual dictionary with an individual regularization parameter for each class. Furthermore, for fast computation, we introduce the orthogonality to column vectors of each dictionary. Since similar patches are collected in the same cluster, accuracy degradation by the orthogonality hardly occurs. Our simulations show that the proposed method outperforms the state-of-the-art in terms of both accuracy and speed.
- 1 January 2015
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E98.A (9) , 1880-1887
High-Quality Recovery of Non-Sparse Signals from Compressed Sensing — Beyond l1 Norm Minimization —
- 1 January 2015
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E98.A (9) , 1880-1887
High-Quality Recovery of Non-Sparse Signals from Compressed Sensing — Beyond l1 Norm Minimization —
- 1 January 2015
- Published by Springer Nature in Sampling Theory in Signal and Image Processing
- Vol. 14 (1) , 17-47
Cadzow Denoising Upgraded: A New Projection Method for the Recovery of Dirac Pulses from Noisy Linear Measurements
- 1 January 2015
- Published by Springer Nature in Sampling Theory in Signal and Image Processing
- Vol. 14 (1) , 17-47
Cadzow Denoising Upgraded: A New Projection Method for the Recovery of Dirac Pulses from Noisy Linear Measurements
- 1 January 2013
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E96.A (12) , 2391-2397
Complex Approximate Message Passing Algorithm for Two-Dimensional Compressed Sensing
- 1 January 2013
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E96.A (12) , 2391-2397
Complex Approximate Message Passing Algorithm for Two-Dimensional Compressed Sensing
- 1 January 2013
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E96.A (10) , 1972-1979
Sampling Signals with Finite Rate of Innovation and Recovery by Maximum Likelihood Estimation
- 1 January 2013
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E96.A (10) , 1972-1979
Sampling Signals with Finite Rate of Innovation and Recovery by Maximum Likelihood Estimation