Both Spatial and Frequency Cues Contribute to High-Fidelity Image Inpainting

• URL: http://arxiv.org/abs/2307.07678v1
• Date: Sat, 15 Jul 2023 01:52:06 GMT
• Title: Both Spatial and Frequency Cues Contribute to High-Fidelity Image Inpainting
• Authors: Ze Lu, Yalei Lv, Wenqi Wang, Pengfei Xiong
• Abstract summary: 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.
• Score: 9.080472817672263
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep generative approaches have obtained great success in image inpainting recently. However, most generative inpainting networks suffer from either over-smooth results or aliasing artifacts. The former lacks high-frequency details, while the latter lacks semantic structure. To address this issue, we propose an effective Frequency-Spatial Complementary Network (FSCN) by exploiting rich semantic information in both spatial and frequency domains. Specifically, we introduce an extra Frequency Branch and Frequency Loss on the spatial-based network to impose direct supervision on the frequency information, and propose a Frequency-Spatial Cross-Attention Block (FSCAB) to fuse multi-domain features and combine the corresponding characteristics. With our FSCAB, the inpainting network is capable of capturing frequency information and preserving visual consistency simultaneously. Extensive quantitative and qualitative experiments demonstrate that our inpainting network can effectively achieve superior results, outperforming previous state-of-the-art approaches with significantly fewer parameters and less computation cost. The code will be released soon.

Related papers

• Exploiting Frequency Correlation for Hyperspectral Image Reconstruction [21.71115793248267]
  Deep priors have emerged as potent methods in hyperspectral image (HSI) reconstruction. We propose a Hyperspectral Frequency Correlation (HFC) prior rooted in in-depth statistical frequency analyses of existent HSI datasets. We then establish the frequency domain learning composed of a Spectral-wise self-Attention of Frequency (SAF) and a Spectral-spatial Interaction of Frequency (SIF)
  arXiv  Detail & Related papers  (2024-06-02T09:36:37Z)
• 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)
• Masked Frequency Modeling for Self-Supervised Visual Pre-Training [102.89756957704138]
  We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models. MFM first masks out a portion of frequency components of the input image and then predicts the missing frequencies on the frequency spectrum. For the first time, MFM demonstrates that, for both ViT and CNN, a simple non-Siamese framework can learn meaningful representations even using none of the following: (i) extra data, (ii) extra model, (iii) mask token.
  arXiv  Detail & Related papers  (2022-06-15T17:58:30Z)
• Wavelet Prior Attention Learning in Axial Inpainting Network [35.06912946192495]
  We propose a novel model -- Wavelet prior attention learning in Axial Inpainting Network (WAIN) The WPA guides the high-level feature aggregation in the multi-scale frequency domain, alleviating the textual artifacts. Stacked ATs employ unmasked clues to help model reasonable features along with low-level features of horizontal and vertical axes.
  arXiv  Detail & Related papers  (2022-06-07T08:45:27Z)
• Adaptive Frequency Learning in Two-branch Face Forgery Detection [66.91715092251258]
  We propose Adaptively learn Frequency information in the two-branch Detection framework, dubbed AFD. We liberate our network from the fixed frequency transforms, and achieve better performance with our data- and task-dependent transform layers.
  arXiv  Detail & Related papers  (2022-03-27T14:25:52Z)
• Exploring Inter-frequency Guidance of Image for Lightweight Gaussian Denoising [1.52292571922932]
  We propose a novel network architecture denoted as IGNet, in order to refine the frequency bands from low to high in a progressive manner. With this design, more inter-frequency prior and information are utilized, thus the model size can be lightened while still perserves competitive results.
  arXiv  Detail & Related papers  (2021-12-22T10:35:53Z)
• 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)
• Focal Frequency Loss for Image Reconstruction and Synthesis [125.7135706352493]
  We show that narrowing gaps in the frequency domain can ameliorate image reconstruction and synthesis quality further. We propose a novel focal frequency loss, which allows a model to adaptively focus on frequency components that are hard to synthesize.
  arXiv  Detail & Related papers  (2020-12-23T17:32:04Z)
• Image inpainting using frequency domain priors [35.54138025375951]
  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.
  arXiv  Detail & Related papers  (2020-12-03T11:08:13Z)

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.