Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting

Transformers have been widely used for video processing owing to the multi-head self attention (MHSA) mechanism. However, the MHSA mechanism encounters an intrinsic difficulty for video inpainting, since the features associated with the corrupted regions are degraded and incur inaccurate self attent...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 46(2024), 7 vom: 30. Juni, Seite 4977-4992
1. Verfasser: Zhang, Kaidong (VerfasserIn)
Weitere Verfasser: Peng, Jialun, Fu, Jingjing, Liu, Dong
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
Beschreibung
Zusammenfassung:Transformers have been widely used for video processing owing to the multi-head self attention (MHSA) mechanism. However, the MHSA mechanism encounters an intrinsic difficulty for video inpainting, since the features associated with the corrupted regions are degraded and incur inaccurate self attention. This problem, termed query degradation, may be mitigated by first completing optical flows and then using the flows to guide the self attention, which was verified in our previous work - flow-guided transformer (FGT). We further exploit the flow guidance and propose FGT++ to pursue more effective and efficient video inpainting. First, we design a lightweight flow completion network by using local aggregation and edge loss. Second, to address the query degradation, we propose a flow guidance feature integration module, which uses the motion discrepancy to enhance the features, together with a flow-guided feature propagation module that warps the features according to the flows. Third, we decouple the transformer along the temporal and spatial dimensions, where flows are used to select the tokens through a temporally deformable MHSA mechanism, and global tokens are combined with the inner-window local tokens through a dual-perspective MHSA mechanism. FGT++ is experimentally evaluated to be outperforming the existing video inpainting networks qualitatively and quantitatively
Beschreibung:Date Revised 06.06.2024
published: Print-Electronic
Citation Status PubMed-not-MEDLINE
ISSN:1939-3539
DOI:10.1109/TPAMI.2024.3361010