HarmoniDPO pairs global and frame-level video features with preference-style optimization to generate audio from silent video, reporting improved synchronization and quality metrics over prior V2A baselines.
In: 25 Proceedings of the AAAI Conference on Artificial Intelligence, vol
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion
HarmoniDPO pairs global and frame-level video features with preference-style optimization to generate audio from silent video, reporting improved synchronization and quality metrics over prior V2A baselines.