Strumming to the Beat: Audio-Conditioned Contrastive Video Textures
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition
Rethinking Contrastive Learning in Session-based Recommendation
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
Subgraph Gaussian Embedding Contrast for Self-Supervised Graph Representation Learning
CellCLAT: Preserving Topology and Trimming Redundancy in Self-Supervised Cellular Contrastive Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.