F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain
- URL: http://arxiv.org/abs/2106.02343v1
- Date: Fri, 4 Jun 2021 08:51:58 GMT
- Title: F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain
- Authors: Shin'ya Yamaguchi and Sekitoshi Kanai
- Abstract summary: We introduce two novel training techniques called frequency dropping (F-Drop) and frequency matching (F-Match)
F-Drop filters out unnecessary high-frequency components from the input images of the discriminators.
F-Match minimizes the difference between real and fake images in the frequency domain for generating more realistic images.
- Score: 12.290010554180613
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Generative adversarial networks built from deep convolutional neural networks
(GANs) lack the ability to exactly replicate the high-frequency components of
natural images. To alleviate this issue, we introduce two novel training
techniques called frequency dropping (F-Drop) and frequency matching (F-Match).
The key idea of F-Drop is to filter out unnecessary high-frequency components
from the input images of the discriminators. This simple modification prevents
the discriminators from being confused by perturbations of the high-frequency
components. In addition, F-Drop makes the GANs focus on fitting in the
low-frequency domain, in which there are the dominant components of natural
images. F-Match minimizes the difference between real and fake images in the
frequency domain for generating more realistic images. F-Match is implemented
as a regularization term in the objective functions of the generators; it
penalizes the batch mean error in the frequency domain. F-Match helps the
generators to fit in the high-frequency domain filtered out by F-Drop to the
real image. We experimentally demonstrate that the combination of F-Drop and
F-Match improves the generative performance of GANs in both the frequency and
spatial domain on multiple image benchmarks (CIFAR, TinyImageNet, STL-10,
CelebA, and ImageNet).
Related papers
- F2former: When Fractional Fourier Meets Deep Wiener Deconvolution and Selective Frequency Transformer for Image Deblurring [8.296475046681696]
We propose a novel approach based on the Fractional Fourier Transform (FRFT), a unified spatial-frequency representation.
We show that the performance of our proposed method is superior to other state-of-the-art (SOTA) approaches.
arXiv Detail & Related papers (2024-09-03T17:05:12Z) - FDCE-Net: Underwater Image Enhancement with Embedding Frequency and Dual Color Encoder [49.79611204954311]
Underwater images often suffer from various issues such as low brightness, color shift, blurred details, and noise due to absorption light and scattering caused by water and suspended particles.
Previous underwater image enhancement (UIE) methods have primarily focused on spatial domain enhancement, neglecting the frequency domain information inherent in the images.
arXiv Detail & Related papers (2024-04-27T15:16:34Z) - Frequency-Aware Deepfake Detection: Improving Generalizability through
Frequency Space Learning [81.98675881423131]
This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images.
Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries.
We introduce a novel frequency-aware approach called FreqNet, centered around frequency domain learning, specifically designed to enhance the generalizability of deepfake detectors.
arXiv Detail & Related papers (2024-03-12T01:28:00Z) - Misalignment-Robust Frequency Distribution Loss for Image Transformation [51.0462138717502]
This paper aims to address a common challenge in deep learning-based image transformation methods, such as image enhancement and super-resolution.
We introduce a novel and simple Frequency Distribution Loss (FDL) for computing distribution distance within the frequency domain.
Our method is empirically proven effective as a training constraint due to the thoughtful utilization of global information in the frequency domain.
arXiv Detail & Related papers (2024-02-28T09:27:41Z) - Both Spatial and Frequency Cues Contribute to High-Fidelity Image
Inpainting [9.080472817672263]
Deep generative approaches have obtained great success in image inpainting recently.
Most generative inpainting networks suffer from either over-smooth results or aliasing artifacts.
We propose an effective Frequency-Spatial Complementary Network (FSCN) by exploiting rich semantic information in both spatial and frequency domains.
arXiv Detail & Related papers (2023-07-15T01:52:06Z) - Efficient Frequency Domain-based Transformers for High-Quality Image
Deblurring [39.720032882926176]
We present an effective and efficient method that explores the properties of Transformers in the frequency domain for high-quality image deblurring.
We formulate the proposed FSAS and DFFN into an asymmetrical network based on an encoder and decoder architecture.
arXiv Detail & Related papers (2022-11-22T13:08:03Z) - TBNet:Two-Stream Boundary-aware Network for Generic Image Manipulation
Localization [49.521622399483846]
We propose a novel end-to-end two-stream boundary-aware network (abbreviated as TBNet) for generic image manipulation localization.
The proposed TBNet can significantly outperform state-of-the-art generic image manipulation localization methods in terms of both MCC and F1.
arXiv Detail & Related papers (2021-08-10T08:22:05Z) - Wavelet-Based Network For High Dynamic Range Imaging [64.66969585951207]
Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal.
In this work, we propose a novel frequency-guided end-to-end deep neural network (FNet) to conduct HDR fusion in the frequency domain, and Wavelet Transform (DWT) is used to decompose inputs into different frequency bands.
The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details.
arXiv Detail & Related papers (2021-08-03T12:26:33Z) - WaveFill: A Wavelet-based Generation Network for Image Inpainting [57.012173791320855]
WaveFill is a wavelet-based inpainting network that decomposes images into multiple frequency bands.
WaveFill decomposes images by using discrete wavelet transform (DWT) that preserves spatial information naturally.
It applies L1 reconstruction loss to the low-frequency bands and adversarial loss to high-frequency bands, hence effectively mitigate inter-frequency conflicts.
arXiv Detail & Related papers (2021-07-23T04:44:40Z) - Are High-Frequency Components Beneficial for Training of Generative
Adversarial Networks [11.226288436817956]
Generative Adversarial Networks (GANs) have the ability to generate realistic images that are visually indistinguishable from real images.
Recent studies of the image spectrum have demonstrated that generated and real images share significant differences at high frequency.
We propose two preprocessing methods eliminating high-frequency differences in GANs training.
arXiv Detail & Related papers (2021-03-20T04:37:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.