# Deep Video Inpainting Guided by Audio-Visual Self-Supervision

arXiv: https://arxiv.org/abs/2310.07663 · HTML: https://mlsanity.com/paper/2310.07663/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Builds on (most cited first, 17 of 17)

- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Look, Listen and Learn](https://mlsanity.com/paper/1705.08168/) (2017)
- [The Sound of Pixels](https://mlsanity.com/paper/1804.03160/) (2018)
- [Objects that Sound](https://mlsanity.com/paper/1712.06651/) (2017)
- [Localizing Visual Sounds the Hard Way](https://mlsanity.com/paper/2104.02691/) (2021)
- [Learning Joint Spatial-Temporal Transformations for Video Inpainting](https://mlsanity.com/paper/2007.10247/) (2020)
- [Deep Flow-Guided Video Inpainting](https://mlsanity.com/paper/1905.02884/) (2019)
- [Deep Video Inpainting](https://mlsanity.com/paper/1905.01639/) (2019)
- [Flow-edge Guided Video Completion](https://mlsanity.com/paper/2009.01835/) (2020)
- [Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching](https://mlsanity.com/paper/2010.05466/) (2020)
- [Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN](https://mlsanity.com/paper/1904.10247/) (2019)
- [Video Inpainting by Jointly Learning Temporal Structure and Spatial Details](https://mlsanity.com/paper/1806.08482/) (2018)
- [Copy-and-Paste Networks for Deep Video Inpainting](https://mlsanity.com/paper/1908.11587/) (2019)
- [Onion-Peel Networks for Deep Video Completion](https://mlsanity.com/paper/1908.08718/) (2019)
- [Towards Audio to Scene Image Synthesis using Generative Adversarial Network](https://mlsanity.com/paper/1808.04108/) (2018)
- [Learning to Have an Ear for Face Super-Resolution](https://mlsanity.com/paper/1909.12780/) (2019)

## Abstract (arXiv)

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.