paper-with-me

홈 › Papers

Video-to-Audio Generation with Hidden Alignment

2024-07-10 · Manjie Xu, Chenxing Li, Xinyi Tu, Yong Ren, Rilin Chen, Yu Gu, Wei Liang, Dong Yu

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.

📄 PDF Abstract BibTeX arXiv:2407.07464

Code (0)

등록된 구현이 없습니다.

Tasks

Audio GenerationData AugmentationText-to-Video GenerationVideo Generation

Similar Papers 제목 키워드 기반

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation

2025-08-23 · Sizhe Shan, Qiulin Li, Yutao Cui, Miles Yang 외 arxiv

Recent advances in video generation produce visually realistic content, yet the absence of synchronized audio severely compromises immersion. To address key challenges in video-to-audio generation, including multimodal d…

Audio GenerationVideo Generation

Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation

2025-10-28 · Kang Zhang, Trung X. Pham, Suyeon Lee, Axi Niu 외 arxiv

We present MGAudio, a novel flow-based framework for open-domain video-to-audio generation, which introduces model-guided dual-role alignment as a central design principle. Unlike prior approaches that rely on classifier…

Audio Generation

Native Audio-Visual Alignment for Generation

2026-05-28 · Longbin Ji, Guan Wang, Xuan Wei, Chenye Yang 외 arxiv

Joint audio-video generation aims to synthesize temporally synchronized and semantically coherent visual-acoustic content. However, existing open-source methods mainly rely on either dual-tower designs with posterior ali…

Video GenerationVideo Alignment

FoleyGRAM: Video-to-Audio Generation with GRAM-Aligned Multimodal Encoders

2025-10-07 · Riccardo Fosco Gramaccioni, Christian Marinoni, Eleonora Grassucci, Giordano Cicchetti 외 arxiv

In this work, we present FoleyGRAM, a novel approach to video-to-audio generation that emphasizes semantic conditioning through the use of aligned multimodal encoders. Building on prior advancements in video-to-audio gen…

Audio Generation

Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows

2026-03-09 · Shentong Mo, Yibing Song arxiv

Coordinated audio generation based on video inputs typically requires a strict audio-visual (AV) alignment, where both semantics and rhythmics of the generated audio segments shall correspond to those in the video frames…

Contrastive LearningAudio Generation