Kyuyeon Kim, Junsik Jung, Woo Jae Kim, Sung-Eui Yoon

SGVR Lab, College of Computing, KAIST

Abstract

<aside> 💡 Humans can easily imagine a scene from auditory information based on their prior knowledge of audio-visual events. In this paper, we mimic this innate human ability in deep learning models to improve the quality of video inpainting. To implement the prior knowledge, we first train the audio-visual network, which learns the correspondence between auditory and visual information. Then, the audio-visual network is employed as a guider that conveys the prior knowledge of audio-visual correspondence to the video inpainting network. This prior knowledge is transferred through our proposed two novel losses: audio-visual attention loss and audio-visual pseudo-class consistency loss. These two losses further improve the performance of the video inpainting by encouraging the inpainting result to have a high correspondence to its synchronized audio. Experimental results demonstrate that our proposed method can restore a wider domain of video scenes and is particularly effective when the sounding object in the scene is partially blinded.

</aside>

Paper

Deep_Video_Inpainting_Guided_by_Audio_Visual_Self_Supervision_ICASSP.pdf

Demo videos

https://www.youtube.com/watch?v=wlvEb5ImN3M

Code (GitHub)

https://github.com/kyuyeonpooh/Audio-Visual-Deep-Video-Inpainting

Presentation video

https://www.youtube.com/watch?v=5Emz8gZq8oU

Poster

avdvi_icassp2022.pdf