Details

Autor(en) / Beteiligte

• Li, Zhen
• Lu, Cheng-Ze
• Qin, Jianhua
• Guo, Chun-Le
• Cheng, Ming-Ming

Titel

Towards An End-to-End Framework for Flow-Guided Video Inpainting

Ist Teil von

• 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, p.17541-17550

Ort / Verlag

IEEE

Erscheinungsjahr

2022

Quelle

IEEE Electronic Library Online

Beschreibungen/Notizen

• Optical flow, which captures motion information across frames, is exploited in recent video inpainting methods through propagating pixels along its trajectories. However, the hand-crafted flow-based processes in these methods are applied separately to form the whole inpainting pipeline. Thus, these methods are less efficient and rely heavily on the intermediate results from earlier stages. 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. The three modules correspond with the three stages of previous flow-based methods but can be Jointly optimized, leading to a more efficient and effective inpainting process. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods both qualitatively and quantitatively and shows promising efficiency. The code is available at https://github.com/MCG-NKU/E2FGVI.