AlignNet: A Unifying Approach to Audio-Visual Alignment

摘要

We present AlignNet, a model that synchronizes videos with reference audios undernon-uniform and irregularmis- alignments. AlignNet learns the end-to-end dense correspondence between each frame of a video and an audio. Our method is designed according to simple and well- established principles: attention, pyramidal processing, warping, and affinity function. Together with the model, we release a dancing dataset Dance50 for training and evaluation. Qualitative, quantitative and subjective evaluation results on dance-music alignment and speech-lip alignment demonstrate that our method far outperforms the state-of- the-art methods. Code, dataset and sample videos are available at our project page¹.