SPG: Improving Motion Diffusion by Smooth Perturbation Guidance
This work addresses quality issues in motion generation for applications like animation and robotics, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of improving output quality in human motion diffusion models by introducing Smooth Perturbation Guidance (SPG), a test-time method that enhances motion fidelity without requiring additional training, achieving consistent improvements across various model architectures and tasks.
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/