When Distillation Breaks Motion Control: Restoring Generative Trajectories for Fast Video Generators
Training-free motion customization imposes motion patterns from reference videos onto video generators through test-time computation. Most existing methods target full diffusion models, requiring many denoising steps and high computational cost. With the rise of efficient distilled models, a natural question arises: can test-time motion customization be applied directly to distilled generators with their accelerated sampling and efficiency gains? However, our analysis reveals that existing training-free techniques fail on distilled models. Distillation fundamentally alters the denoising dynamics that prior test-time guidance relies on, and the large denoising steps of distilled generators discard the dense intermediate states that score guidance requires, rendering existing motion control strategies incompatible with fast generation. To address this limitation, we propose MotionEcho, a novel training-free test-time distillation framework that enables motion customization for distilled video generators. The key idea is to correct the student model's sampling trajectory with restricted usage of a high-quality diffusion teacher at inference time. Teacher supervises the student's denoising by re-noising the student's endpoint onto its dense trajectory to form a motion-aligned clean endpoint, then interpolating it with the student's, while an adaptive scheduling mechanism determines when and how much teacher guidance is needed. As a result, MotionEcho restores generative trajectories for distilled video generators via lightweight, adaptive test-time teacher guidance, enabling accurate motion control without compromising generation efficiency. Extensive experiments on multiple distilled video generation models demonstrate that our method significantly improves motion fidelity and visual quality while retaining the efficiency advantages of distilled generation.
Code (0)
등록된 구현이 없습니다.
Tasks
Video GenerationSimilar Papers 제목 키워드 기반
Continuous Facial Motion Deblurring
We introduce a novel framework for continuous facial motion deblurring that restores the continuous sharp moment latent in a single motion-blurred face image via a moment control factor. Although a motion-blurred image i…
DeblurringImage DeblurringSingle Image DeblurringVideo DeblurringAdversarially Robust Video Perception by Seeing Motion
Despite their excellent performance, state-of-the-art computer vision models often fail when they encounter adversarial examples. Video perception models tend to be more fragile under attacks, because the adversary has m…
Adversarial RobustnessRestoring Initial Noise Sensitivity in Text-to-Image Distillation via Geometric Alignment
Generative distillation significantly accelerates text-to-image (T2I) generation by compressing multi-step trajectories into few-step student models while preserving perceptual quality. However, existing methods primaril…
Towards Adaptive Humanoid Control via Multi-Behavior Distillation and Reinforced Fine-Tuning
Humanoid robots are promising to learn a diverse set of human-like locomotion behaviors, including standing up, walking, running, and jumping. However, existing methods predominantly require training independent policies…
Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain
Humanoid behavior foundation models aim to acquire reusable whole-body control policies from broad human motion priors, enabling a single controller to produce diverse and expressive behaviors. However, existing motion-c…