Error-Mask-Adaptive Dynamic Filtering for Image Inpainting
A novel error-mask-adaptive dynamic filtering (EMDF) algorithm is proposed in this paper, which uses a continuous error mask to inpaint an image adaptively and faithfully. In an EMDF layer, we determine a spatially varying filter adaptively according to an error mask and perform separable dynamic fi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10845789/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576760200298496 |
|---|---|
| author | Keunsoo Ko Seunggyun Woo Chang-Su Kim |
| author_facet | Keunsoo Ko Seunggyun Woo Chang-Su Kim |
| author_sort | Keunsoo Ko |
| collection | DOAJ |
| description | A novel error-mask-adaptive dynamic filtering (EMDF) algorithm is proposed in this paper, which uses a continuous error mask to inpaint an image adaptively and faithfully. In an EMDF layer, we determine a spatially varying filter adaptively according to an error mask and perform separable dynamic filtering. Meanwhile, we update the error mask by modeling the error propagation during the filtering. Through several EMDF layers, we predict an inpainting result. Finally, we refine it to reconstruct a more faithful image. Experimental results on diverse datasets show that the proposed EMDF algorithm outperforms existing inpainting algorithms significantly. The source codes are available at <uri>https://github.com/keunsoo-ko/EMDF</uri>. |
| format | Article |
| id | doaj-art-66b721064c0d45ef83fa8103557df0d7 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-66b721064c0d45ef83fa8103557df0d72025-01-31T00:02:06ZengIEEEIEEE Access2169-35362025-01-0113184031841710.1109/ACCESS.2025.353144010845789Error-Mask-Adaptive Dynamic Filtering for Image InpaintingKeunsoo Ko0https://orcid.org/0000-0003-0203-4530Seunggyun Woo1https://orcid.org/0009-0002-0722-2290Chang-Su Kim2https://orcid.org/0000-0002-4276-1831Department of Artificial Intelligence, The Catholic University of Korea, Bucheon, South KoreaSchool of Electrical Engineering, Korea University, Seoul, South KoreaSchool of Electrical Engineering, Korea University, Seoul, South KoreaA novel error-mask-adaptive dynamic filtering (EMDF) algorithm is proposed in this paper, which uses a continuous error mask to inpaint an image adaptively and faithfully. In an EMDF layer, we determine a spatially varying filter adaptively according to an error mask and perform separable dynamic filtering. Meanwhile, we update the error mask by modeling the error propagation during the filtering. Through several EMDF layers, we predict an inpainting result. Finally, we refine it to reconstruct a more faithful image. Experimental results on diverse datasets show that the proposed EMDF algorithm outperforms existing inpainting algorithms significantly. The source codes are available at <uri>https://github.com/keunsoo-ko/EMDF</uri>.https://ieeexplore.ieee.org/document/10845789/Image inpaintingdynamic filteringmask-adaptive filteringconvolutional neural networks |
| spellingShingle | Keunsoo Ko Seunggyun Woo Chang-Su Kim Error-Mask-Adaptive Dynamic Filtering for Image Inpainting IEEE Access Image inpainting dynamic filtering mask-adaptive filtering convolutional neural networks |
| title | Error-Mask-Adaptive Dynamic Filtering for Image Inpainting |
| title_full | Error-Mask-Adaptive Dynamic Filtering for Image Inpainting |
| title_fullStr | Error-Mask-Adaptive Dynamic Filtering for Image Inpainting |
| title_full_unstemmed | Error-Mask-Adaptive Dynamic Filtering for Image Inpainting |
| title_short | Error-Mask-Adaptive Dynamic Filtering for Image Inpainting |
| title_sort | error mask adaptive dynamic filtering for image inpainting |
| topic | Image inpainting dynamic filtering mask-adaptive filtering convolutional neural networks |
| url | https://ieeexplore.ieee.org/document/10845789/ |
| work_keys_str_mv | AT keunsooko errormaskadaptivedynamicfilteringforimageinpainting AT seunggyunwoo errormaskadaptivedynamicfilteringforimageinpainting AT changsukim errormaskadaptivedynamicfilteringforimageinpainting |