Video-to-Audio Generation with Hidden Alignment
This work addresses the problem of generating synchronized audio from video for researchers in audio-visual generation, but it appears incremental as it builds on existing paradigms with ablation studies.
The paper tackled video-to-audio generation by exploring vision encoders, auxiliary embeddings, and data augmentation, demonstrating state-of-the-art capabilities with a focus on generation quality and synchronization alignment.
Generating semantically and temporally aligned audio content in accordance with video input has become a focal point for researchers, particularly following the remarkable breakthrough in text-to-video generation. In this work, we aim to offer insights into the video-to-audio generation paradigm, focusing on three crucial aspects: vision encoders, auxiliary embeddings, and data augmentation techniques. Beginning with a foundational model built on a simple yet surprisingly effective intuition, we explore various vision encoders and auxiliary embeddings through ablation studies. Employing a comprehensive evaluation pipeline that emphasizes generation quality and video-audio synchronization alignment, we demonstrate that our model exhibits state-of-the-art video-to-audio generation capabilities. Furthermore, we provide critical insights into the impact of different data augmentation methods on enhancing the generation framework's overall capacity. We showcase possibilities to advance the challenge of generating synchronized audio from semantic and temporal perspectives. We hope these insights will serve as a stepping stone toward developing more realistic and accurate audio-visual generation models.