Efficient guided inpainting of larger hole missing images based on hierarchical decoding network
Abstract When dealing with images containing large hole-missing regions, deep learning-based image inpainting algorithms often face challenges such as local structural distortions and blurriness. In this paper, a novel hierarchical decoding network for image inpainting is proposed. Firstly, the stru...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-01-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01686-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861474741714944 |
|---|---|
| author | Xiucheng Dong Yaling Ju Dangcheng Zhang Bing Hou Jinqing He |
| author_facet | Xiucheng Dong Yaling Ju Dangcheng Zhang Bing Hou Jinqing He |
| author_sort | Xiucheng Dong |
| collection | DOAJ |
| description | Abstract When dealing with images containing large hole-missing regions, deep learning-based image inpainting algorithms often face challenges such as local structural distortions and blurriness. In this paper, a novel hierarchical decoding network for image inpainting is proposed. Firstly, the structural priors extracted from the encoding layer are utilized to guide the first decoding layer, while residual blocks are employed to extract deep-level image features. Secondly, multiple hierarchical decoding layers progressively fill in the missing regions from top to bottom, then interlayer features and gradient priors are used to guide information transfer between layers. Furthermore, a proposed Multi-dimensional Efficient Attention is introduced for feature fusion, enabling more effective extraction of image features across different dimensions compared to conventional methods. Finally, Efficient Context Fusion combines the reconstructed feature maps from different decoding layers into the image space, preserving the semantic integrity of the output image. Experiments have been conducted to validate the effectiveness of the proposed method, demonstrating superior performance in both subjective and objective evaluations. When inpainting images with missing regions ranging from 50% to 60%, the proposed method achieves improvements of 0.02 dB (0.22 dB) and 0.001 (0.003) in PSNR and SSIM, on the CelebA-HQ (Places2) dataset, respectively. |
| format | Article |
| id | doaj-art-6fedca3ed8774a7eaea8ac2b816eb0ca |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-6fedca3ed8774a7eaea8ac2b816eb0ca2025-02-09T13:01:20ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-01-0111211610.1007/s40747-024-01686-8Efficient guided inpainting of larger hole missing images based on hierarchical decoding networkXiucheng Dong0Yaling Ju1Dangcheng Zhang2Bing Hou3Jinqing He4Sichuan University Jinjiang CollegeSchool of Electrical Engineering and Electronic Information, Xihua UniversitySchool of Electrical Engineering and Electronic Information, Xihua UniversitySchool of Electrical Engineering and Electronic Information, Xihua UniversitySchool of Electrical Engineering and Electronic Information, Xihua UniversityAbstract When dealing with images containing large hole-missing regions, deep learning-based image inpainting algorithms often face challenges such as local structural distortions and blurriness. In this paper, a novel hierarchical decoding network for image inpainting is proposed. Firstly, the structural priors extracted from the encoding layer are utilized to guide the first decoding layer, while residual blocks are employed to extract deep-level image features. Secondly, multiple hierarchical decoding layers progressively fill in the missing regions from top to bottom, then interlayer features and gradient priors are used to guide information transfer between layers. Furthermore, a proposed Multi-dimensional Efficient Attention is introduced for feature fusion, enabling more effective extraction of image features across different dimensions compared to conventional methods. Finally, Efficient Context Fusion combines the reconstructed feature maps from different decoding layers into the image space, preserving the semantic integrity of the output image. Experiments have been conducted to validate the effectiveness of the proposed method, demonstrating superior performance in both subjective and objective evaluations. When inpainting images with missing regions ranging from 50% to 60%, the proposed method achieves improvements of 0.02 dB (0.22 dB) and 0.001 (0.003) in PSNR and SSIM, on the CelebA-HQ (Places2) dataset, respectively.https://doi.org/10.1007/s40747-024-01686-8Hierarchical decoding networkGradient priorsMulti-dimensional efficient attentionEfficient context fusion |
| spellingShingle | Xiucheng Dong Yaling Ju Dangcheng Zhang Bing Hou Jinqing He Efficient guided inpainting of larger hole missing images based on hierarchical decoding network Complex & Intelligent Systems Hierarchical decoding network Gradient priors Multi-dimensional efficient attention Efficient context fusion |
| title | Efficient guided inpainting of larger hole missing images based on hierarchical decoding network |
| title_full | Efficient guided inpainting of larger hole missing images based on hierarchical decoding network |
| title_fullStr | Efficient guided inpainting of larger hole missing images based on hierarchical decoding network |
| title_full_unstemmed | Efficient guided inpainting of larger hole missing images based on hierarchical decoding network |
| title_short | Efficient guided inpainting of larger hole missing images based on hierarchical decoding network |
| title_sort | efficient guided inpainting of larger hole missing images based on hierarchical decoding network |
| topic | Hierarchical decoding network Gradient priors Multi-dimensional efficient attention Efficient context fusion |
| url | https://doi.org/10.1007/s40747-024-01686-8 |
| work_keys_str_mv | AT xiuchengdong efficientguidedinpaintingoflargerholemissingimagesbasedonhierarchicaldecodingnetwork AT yalingju efficientguidedinpaintingoflargerholemissingimagesbasedonhierarchicaldecodingnetwork AT dangchengzhang efficientguidedinpaintingoflargerholemissingimagesbasedonhierarchicaldecodingnetwork AT binghou efficientguidedinpaintingoflargerholemissingimagesbasedonhierarchicaldecodingnetwork AT jinqinghe efficientguidedinpaintingoflargerholemissingimagesbasedonhierarchicaldecodingnetwork |