In this paper, we propose an End-to-End framework for Flow-Guided Video Inpainting (E 2 FGVI) through elaborately designed three trainable modules, namely, flow completion, feature propagation, and content hallucination modules.
2022: Z. Li, Cheng Lu, Jia Qin, Chunle Guo, Mingg-Ming Cheng
Ranked #1 on Video Inpainting on YouTube-VOS 2018 val
https://arxiv.org/pdf/2204.02663v2.pdf
view more