Strumming to the Beat: Audio-Conditioned Contrastive Video Textures

TL;DR

This paper presents a contrastive learning-based method for infinite video texture synthesis that can incorporate audio cues, producing diverse, smooth, and synchronized videos from a single input.

Contribution

It introduces a non-parametric, contrastive learning approach for video texture synthesis that extends to audio-conditioned generation without fine-tuning.

Findings

Outperforms baselines on perceptual quality

Handles diverse input videos effectively

Synthesizes audio-visual synchronized videos

Abstract

We introduce a non-parametric approach for infinite video texture synthesis using a representation learned via contrastive learning. We take inspiration from Video Textures, which showed that plausible new videos could be generated from a single one by stitching its frames together in a novel yet consistent order. This classic work, however, was constrained by its use of hand-designed distance metrics, limiting its use to simple, repetitive videos. We draw on recent techniques from self-supervised learning to learn this distance metric, allowing us to compare frames in a manner that scales to more challenging dynamics, and to condition on other data, such as audio. We learn representations for video frames and frame-to-frame transition probabilities by fitting a video-specific model trained using contrastive learning. To synthesize a texture, we randomly sample frames with high transition probabilities to generate diverse temporally smooth videos with novel sequences and transitions. The model naturally extends to an audio-conditioned setting without requiring any finetuning. Our model outperforms baselines on human perceptual scores, can handle a diverse range of input videos, and can combine semantic and audio-visual cues in order to synthesize videos that synchronize well with an audio signal.