CVLGSDOct 24, 2019

Vision-Infused Deep Audio Inpainting

arXiv:1910.10997v192 citations
Originality Highly original
AI Analysis

This work addresses the problem of multi-modality perception for interactive intelligence, introducing a novel task that combines visual and audio data for inpainting.

The paper tackles the task of synthesizing missing audio segments using visual information from accompanying videos, achieving realistic and coherent audio inpainting as demonstrated through extensive experiments.

Multi-modality perception is essential to develop interactive intelligence. In this work, we consider a new task of visual information-infused audio inpainting, \ie synthesizing missing audio segments that correspond to their accompanying videos. We identify two key aspects for a successful inpainter: (1) It is desirable to operate on spectrograms instead of raw audios. Recent advances in deep semantic image inpainting could be leveraged to go beyond the limitations of traditional audio inpainting. (2) To synthesize visually indicated audio, a visual-audio joint feature space needs to be learned with synchronization of audio and video. To facilitate a large-scale study, we collect a new multi-modality instrument-playing dataset called MUSIC-Extra-Solo (MUSICES) by enriching MUSIC dataset. Extensive experiments demonstrate that our framework is capable of inpainting realistic and varying audio segments with or without visual contexts. More importantly, our synthesized audio segments are coherent with their video counterparts, showing the effectiveness of our proposed Vision-Infused Audio Inpainter (VIAI). Code, models, dataset and video results are available at https://hangz-nju-cuhk.github.io/projects/AudioInpainting

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes