Neural Audio Generation from Video via Negative Audio Guidance (FAFSA)

Curtis Hu (UC Berkeley)

paper, code, demo

Abstract

We propose a novel approach for generating audio from video using a diffusion model guided by negative audio.

Demos

Results

BibTeX

@inproceedings{hayakawa2026step,
  title     = {Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance},
  author    = {Hayakawa, Akio and Ishii, Masato and Shibuya, Takashi and Mitsufuji, Yuki},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year      = {2026}
}