MotionCFG：通过语义运动锐化增强视频生成运动动态

View PDF HTML (experimental)

Abstract:Despite recent advancements in Text-to-Video (T2V) synthesis, generating high-fidelity and dynamic motion remains a significant challenge. Existing methods primarily rely on Classifier-Free Guidance (CFG), but standard CFG treats all semantic dimensions uniformly and provides no mechanism to selectively resolve ambiguity along the motion axis. To address this, we propose MotionCFG, a training-free approach that introduces selective guidance along the motion subspace of the condition embedding. Specifically, we construct a motion-perturbed negative condition by injecting Gaussian noise into motion-related embeddings, and steer generation away from it to selectively amplify motion intent. We show theoretically that this procedure implicitly approximates Semantic Laplacian Sharpening, a second-order correction that suppresses motion-ambiguous regions of the score landscape and amplifies well-resolved dynamic peaks. Combined with a piecewise guidance schedule that confines intervention to the early denoising steps, MotionCFG consistently improves motion dynamics across state-of-the-art T2V frameworks with negligible overhead. We further demonstrate that this Laplacian sharpening principle generalizes beyond motion, effectively steering complex, non-linear concepts such as precise object numerosity that are typically difficult to modulate via standard text-based guidance. Our project page is available at this https URL.

Comments:	Accepted to NeurIPS 2026
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:	arXiv:2603.14073 [cs.CV]
	(or arXiv:2603.14073v2 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2603.14073 arXiv-issued DOI via DataCite

Submission history

From: Jong Chul Ye [view email]
[v1] Sat, 14 Mar 2026 18:39:37 UTC (34,791 KB)
[v2] Tue, 10 Nov 2026 19:48:55 UTC (28,010 KB)