Tri Ton, Ji Woo Hong, Chang D. Yoo. TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-To-Audio Synthesis. In IEEE/CVF International Conference on Computer Vision, ICCV 2025, Honolulu, HI, USA, October 19-25, 2025. pages 14228-14237, IEEE, 2025. [doi]
Abstract is missing.