Consistent Image Inpainting with Pre-Perception and Cross-Perception Collaborative Processes

It has been proven that introducing multiple guidance sources boosts image inpainting performance. However, existing methods primarily focus on local relationships and neglect the holistic interplay between guidance and texture information. Moreover, they lack an effective feedback mechanism to adap...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - PP(2025) vom: 21. Okt.
Auteur principal: Zhang, Yongle (Auteur)
Autres auteurs: Liu, Yimin, Fan, Hao, Hu, Ruotong, Zhang, Jian, Wu, Qiang
Format: Article en ligne
Langue:English
Publié: 2025
Accès à la collection:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sujets:Journal Article
LEADER 01000naa a22002652c 4500
001 NLM394357760
003 DE-627
005 20251023232442.0
007 cr uuu---uuuuu
008 251023s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2025.3622071  |2 doi 
028 5 2 |a pubmed25n1607.xml 
035 |a (DE-627)NLM394357760 
035 |a (NLM)41118280 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Zhang, Yongle  |e verfasserin  |4 aut 
245 1 0 |a Consistent Image Inpainting with Pre-Perception and Cross-Perception Collaborative Processes 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 21.10.2025 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a It has been proven that introducing multiple guidance sources boosts image inpainting performance. However, existing methods primarily focus on local relationships and neglect the holistic interplay between guidance and texture information. Moreover, they lack an effective feedback mechanism to adaptively update the guidance process as corrupted texture information is progressively restored, potentially resulting in inconsistent inpainting. To tackle this issue, we propose a novel scheme aligned with pre-perception and cross-perception collaborative processes in human drawing. To mimic the pre-perception process, we introduce a pre-perceptual transformer block that captures long-range contextual dependencies and activates meaningful information to individually optimize image structures, semantic layouts, and textures, thereby effectively controlling their respective generation. To mimic the cross-perception collaborative process, we propose a cyclic cross-perceptual interaction to maintain consistency across the entire image regarding structure, layout, and texture while progressively refining their details. This interaction accounts for the global attention relationship between texture and other guidance sources (including image structure and semantic layout) to enhance image texture, alongside integrating a dedicated feedback mechanism to update guidance information. The proposed components are alternately deployed in three-branch decoders of the new scheme from rough to fine-grained levels to achieve these two iterative processes of human drawing. Experimental results prove the superiority of the proposed scheme over state-of-the-art methods across three datasets 
650 4 |a Journal Article 
700 1 |a Liu, Yimin  |e verfasserin  |4 aut 
700 1 |a Fan, Hao  |e verfasserin  |4 aut 
700 1 |a Hu, Ruotong  |e verfasserin  |4 aut 
700 1 |a Zhang, Jian  |e verfasserin  |4 aut 
700 1 |a Wu, Qiang  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g PP(2025) vom: 21. Okt.  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnas 
773 1 8 |g volume:PP  |g year:2025  |g day:21  |g month:10 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2025.3622071  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2025  |b 21  |c 10