通过平滑扰动提升动作扩散模型质量，无需额外训练。
SPG: Improving Motion Diffusion by Smooth Perturbation Guidance
- 用时间平滑构建弱模型实现负向引导。
- 在多个模型架构上显著提高动作保真度。
- 适合需要高质量动作生成的研究者使用。
本文提出一种测试时引导方法，无需额外训练即可提升人体动作扩散模型的输出质量。为实现负向引导，平滑扰动引导（SPG）通过在去噪步骤中对动作进行时间平滑构建弱模型。与源自图像生成领域的模型无关方法相比，SPG在扰动动作扩散模型时有效缓解了分布外问题。在SPG引导下，动作结构特性得以保持。该工作在不同模型架构和任务上进行了全面分析，尽管实现极其简单且无需额外训练，但SPG始终能提升动作保真度。项目页面见 https://spg-blind.vercel.app/
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。