Audio-video (AV) generation has recently made strong progress in perceptual quality and multimodal coherence, yet generating content with plausible motion-sound relations remains challenging. Existing methods often produce object motions that are visually unstable and sounds that are only loosely aligned with salient motion or contact events, largely because they lack an explicit motion-aware structure shared by video and audio generation. We present Tora3, a trajectory-guided AV generation framework that improves physical coherence by using object trajectories as a shared kinematic prior. Rather than treating trajectories as a video-only control signal, Tora3 uses them to jointly guide visual motion and acoustic events. Specifically, we design a trajectory-aligned motion representation for video, a kinematic-audio alignment module driven by trajectory-derived second-order kinematic states, and a hybrid flow matching scheme that preserves trajectory fidelity in trajectory-conditioned regions while maintaining local coherence elsewhere. We further curate PAV, a large-scale AV dataset emphasizing motion-relevant patterns with automatically extracted motion annotations. Extensive experiments show that Tora3 improves motion realism, motion-sound synchronization, and overall AV generation quality over strong open-source baselines.

翻译：音频-视频（AV）生成技术近期在感知质量与多模态一致性方面取得了显著进展，但生成具备合理运动-声音关系的内容仍具挑战性。现有方法通常产生视觉上不稳定的物体运动，并且声音仅与显著运动或接触事件松散对齐，主要原因在于其缺乏视频和音频生成所共享的显式运动感知结构。我们提出Tora3，一个基于轨迹引导的音频-视频生成框架，通过将物体轨迹作为共享的运动学先验来提升物理一致性。Tora3并未将轨迹视为仅用于视频的控制信号，而是利用轨迹联合引导视觉运动与声学事件。具体而言，我们设计了用于视频的轨迹对齐运动表征、由轨迹派生的二阶运动状态驱动的运动学-音频对齐模块，以及一种混合流匹配方案，该方案在轨迹条件区域保持轨迹保真度，同时在其他区域维持局部一致性。此外，我们构建了PAV数据集，这是一个大规模音频-视频数据集，其重点在于运动相关模式并带有自动提取的运动标注。大量实验表明，Tora3在运动真实性、运动-声音同步性以及整体音频-视频生成质量方面均优于强大的开源基线方法。