MotionSpec: Spectral Trajectory Supervision for Motion-Consistent Video Generation

2026-09-23

AI Summary

为解决视频生成中的运动不一致问题，提出MotionSpec方法，通过频谱轨迹一致性(STC)和局部流一致性(LFC)增强视频的运动连贯性和真实性。

Abstract

Recent advances in text-to-video generation have enabled high-fidelity visual synthesis, yet realistic motion remains challenging. Generated videos may exhibit temporal discontinuities, inconsistent action progression, and structural distortions during complex movements. Even when individual frames appear realistic, the underlying motion may evolve in inconsistent or implausible ways. Standard generative objectives provide limited motion-specific supervision, leaving motion evolution insufficiently constrained. In this paper, we propose MotionSpec, a motion supervision framework centered on Spectral Trajectory Consistency (STC). STC constructs dense anchor-relative motion trajectories and transforms them into motion spectral volumes via a temporal Fourier transform. By aligning the spectral amplitude and phase of predicted and target trajectories, STC constrains both motion strength across temporal frequencies and the temporal organization of motion. To complement this trajectory-level supervision, we introduce Local Flow Consistency (LFC), which aligns consecutive-frame optical flow between predicted and target videos to stabilize local motion transitions. Experiments demonstrate that MotionSpec consistently improves motion consistency, temporal coherence, and plausibility while preserving visual fidelity.

Problem

• text-to-video generation
• motion consistency
• temporal discontinuities
• action progression
• structural distortions

Innovation

• Spectral Trajectory Consistency
• Temporal Fourier Transform
• Local Flow Consistency