FSTT: Flow-Guided Spatial Temporal Transformer for Deep Video Inpainting
Video inpainting aims to complete the missing regions with content that is consistent both spatially and temporally. How to effectively utilize the spatio-temporal information in videos is critical for video inpainting. Recent advances in video inpainting methods combine both optical flow and transf...
Main Authors: | Ruixin Liu, Yuesheng Zhu |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/21/4452 |
Similar Items
-
Learning a spatial-temporal texture transformer network for video inpainting
by: Pengsen Ma, et al.
Published: (2022-10-01) -
Deep Transformer Based Video Inpainting Using Fast Fourier Tokenization
by: Taewan Kim, et al.
Published: (2024-01-01) -
Coherent Semantic Spatial-Temporal Attention Network for Video Inpainting
by: LIU Lang, LI Liang, DAN Yuan-hong
Published: (2021-10-01) -
Spatio-temporal image inpainting for video applications
by: Voronin Viacheslav, et al.
Published: (2017-01-01) -
Improvement in video inpainting in presence of moving subjects
by: A. Ghanbari Talouki, et al.
Published: (2019-12-01)