# MotionSpec: Spectral Trajectory Supervision for Motion-Consistent Video Generation

arXiv: https://arxiv.org/abs/2609.28095 · HTML: https://mlsanity.com/paper/2609.28095/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 23 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation](https://mlsanity.com/paper/2407.02371/) (2024)
- [MotionDirector: Motion Customization of Text-to-Video Diffusion Models](https://mlsanity.com/paper/2310.08465/) (2023)
- [VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models](https://mlsanity.com/paper/2502.02492/) (2025)
- [FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://mlsanity.com/paper/2312.07537/) (2023)
- [Generative Image Dynamics](https://mlsanity.com/paper/2309.07906/) (2023)
- [VMBench: A Benchmark for Perception-Aligned Video Motion Generation](https://mlsanity.com/paper/2503.10076/) (2025)
- [Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation](https://mlsanity.com/paper/2412.06016/) (2024)
- [AnimateAnything: Consistent and Controllable Animation for Video Generation](https://mlsanity.com/paper/2411.10836/) (2024)
- [Spectral Motion Alignment for Video Motion Transfer using Diffusion Models](https://mlsanity.com/paper/2403.15249/) (2024)
- [Optical-Flow Guided Prompt Optimization for Coherent Video Generation](https://mlsanity.com/paper/2411.15540/) (2024)
- [MotiF: Making Text Count in Image Animation with Motion Focal Loss](https://mlsanity.com/paper/2412.16153/) (2024)
- [Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning](https://mlsanity.com/paper/2410.24219/) (2024)
- [FREAK: Frequency-modulated High-fidelity and Real-time Audio-driven Talking Portrait Synthesis](https://mlsanity.com/paper/2503.04067/) (2025)
- [Latent Temporal Discrepancy as Motion Prior: A Loss-Weighting Strategy for Dynamic Fidelity in T2V](https://mlsanity.com/paper/2601.20504/) (2026)
- [FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models](https://mlsanity.com/paper/2504.14535/) (2025)
- [Physics-Guided Motion Loss for Video Generation Model](https://mlsanity.com/paper/2506.02244/) (2025)

## Built on by (most cited first, 1 of 1)

- [How Does Geometry Enter Generated Motion?](https://mlsanity.com/paper/2610.05135/) (2026)

## Abstract (arXiv)

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.