Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence
2026-04-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMultimediaSound
AI summaryⓘ
The authors created Tora3, a new method that helps make videos with sound where the movements and noises match up better. They use the paths that objects take (called trajectories) to guide both the video and the sound, making the motion look more real and the sounds happen at the right times. They also made a big dataset called PAV to help train and test their approach. Their experiments show Tora3 makes better and more believable audio-video content compared to existing methods.
audio-video generationtrajectorykinematicsmotion-sound synchronizationvideo generationacoustic eventsflow matchingmultimodal coherencedatasets
Authors
Junchao Liao, Zhenghao Zhang, Xiangyu Meng, Litao Li, Ziying Zhang, Siyu Zhu, Long Qin, Weizhi Wang
Abstract
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.