Year: 2025
Type: preprint
Abstract: This paper presents a test-time guidance method to improve the output quality of the human motion diffusion models without requiring additional training. To have negative guidance, Smooth Perturbation Guidance (SPG) builds a weak model by temporally smoothing the motion in the denoising steps. Compared to model-agnostic methods originating from the image generation field, SPG effectively mitigates out-of-distribution issues when perturbing motion diffusion models. In SPG guidance, the nature of motion structure remains intact. This work conducts a comprehensive analysis across distinct model architectures and tasks. Despite its extremely simple implementation and no need for additional training requirements, SPG consistently enhances motion fidelity. Project page can be found at https://spg-blind.vercel.app/
Source: arXiv (Cornell University)
Author: Jeon, Boseong
Language: English
Topic: Human Motion and Animation
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4415335356
Cites:
Cited by:
Related to: