Deep video inpainting guided by audio-visual self-supervision

Abstract

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 to learn 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 – that further improve the performance of the video inpainting network. These two losses encourage 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. This thesis is based on the author’s original paper [1].