Image inpainting using frequency domain priors
- URL: http://arxiv.org/abs/2012.01832v1
- Date: Thu, 3 Dec 2020 11:08:13 GMT
- Title: Image inpainting using frequency domain priors
- Authors: Hiya Roy, Subhajit Chaudhury, Toshihiko Yamasaki, Tatsuaki Hashimoto
- Abstract summary: We present a novel image inpainting technique using frequency domain information.
We evaluate our proposed method on the publicly available datasets CelebA, Paris Streetview, and DTD texture dataset.
- Score: 35.54138025375951
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this paper, we present a novel image inpainting technique using frequency
domain information. Prior works on image inpainting predict the missing pixels
by training neural networks using only the spatial domain information. However,
these methods still struggle to reconstruct high-frequency details for real
complex scenes, leading to a discrepancy in color, boundary artifacts,
distorted patterns, and blurry textures. To alleviate these problems, we
investigate if it is possible to obtain better performance by training the
networks using frequency domain information (Discrete Fourier Transform) along
with the spatial domain information. To this end, we propose a frequency-based
deconvolution module that enables the network to learn the global context while
selectively reconstructing the high-frequency components. We evaluate our
proposed method on the publicly available datasets CelebA, Paris Streetview,
and DTD texture dataset, and show that our method outperforms current
state-of-the-art image inpainting techniques both qualitatively and
quantitatively.
Related papers
- Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning [86.99944014645322]
We introduce a novel framework, Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning.
We decompose each query image into its high-frequency and low-frequency components, and parallel incorporate them into the feature embedding network.
Our framework establishes new state-of-the-art results on multiple cross-domain few-shot learning benchmarks.
arXiv Detail & Related papers (2024-11-03T04:02:35Z) - 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) - Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Models [89.76587063609806]
We study the denoising diffusion probabilistic model (DDPM) in wavelet space, instead of pixel space, for visual synthesis.
By explicitly modeling the wavelet signals, we find our model is able to generate images with higher quality on several datasets.
arXiv Detail & Related papers (2023-07-27T06:53:16Z) - 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) - Unsupervised Domain Transfer with Conditional Invertible Neural Networks [83.90291882730925]
We propose a domain transfer approach based on conditional invertible neural networks (cINNs)
Our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood.
Our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks.
arXiv Detail & Related papers (2023-03-17T18:00:27Z) - DPFNet: A Dual-branch Dilated Network with Phase-aware Fourier
Convolution for Low-light Image Enhancement [1.2645663389012574]
Low-light image enhancement is a classical computer vision problem aiming to recover normal-exposure images from low-light images.
convolutional neural networks commonly used in this field are good at sampling low-frequency local structural features in the spatial domain.
We propose a novel module using the Fourier coefficients, which can recover high-quality texture details under the constraint of semantics in the frequency phase.
arXiv Detail & Related papers (2022-09-16T13:56:09Z) - 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) - Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting [42.189768203036394]
We make the first attempt towards universal detection of deep inpainting, where the detection network can generalize well.
Our approach outperforms existing detection methods by a large margin and generalizes well to unseen deep inpainting techniques.
arXiv Detail & Related papers (2021-06-03T01:29:29Z) - Restore from Restored: Single-image Inpainting [9.699531255678856]
We present a novel and efficient self-supervised fine-tuning algorithm for inpainting networks.
We upgrade the parameters of the pretrained networks by utilizing existing self-similar patches within the given input image.
We achieve state-of-the-art inpainting results on publicly available benchmark datasets.
arXiv Detail & Related papers (2021-02-16T10:59:28Z) - Frequency learning for image classification [1.9336815376402716]
This paper presents a new approach for exploring the Fourier transform of the input images, which is composed of trainable frequency filters.
We propose a slicing procedure to allow the network to learn both global and local features from the frequency-domain representations of the image blocks.
arXiv Detail & Related papers (2020-06-28T00:32:47Z)
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.