Search papers, labs, and topics across Lattice.
This paper introduces Motion-Inference-as-Control (MIC), a novel training-free framework for human motion generation that effectively manages both continuous objective-based and discontinuous criterion-based constraints. By framing motion generation as a stochastic control problem, MIC enables flexible enforcement of diverse motion requirements without the need for differentiable losses. Experimental results across various constraint scenarios validate the framework's ability to adaptively balance and reconcile different motion constraints during generation, marking a significant advancement in controllable motion synthesis.
Training-free motion generation can now flexibly handle both continuous and discontinuous constraints without requiring differentiability, revolutionizing how we approach human motion synthesis.
Training-free controllable motion generation has attracted growing interest for enabling flexible constraint enforcement without constraint-specific training. However, existing training-free methods require constraints to be continuous objective-based with differentiable losses, while many real-world requirements are criterion-based and provide only discontinuous, sparse, or even black-box feedback. In this paper, we propose Motion-Inference-as-Control (MIC), the first training-free motion generation framework that handles both continuous objective-based and criterion-based motion constraints under a shared mechanism. The key idea is to cast diffusion-based motion generation as a stochastic control problem. This perspective not only provides principled and practically effective step-wise control laws that support criterion-based constraints without requiring differentiability and naturally accommodate objective-based constraints as a special case, but also motivates a control-oriented constraint coordination mechanism that adaptively balances and reconciles motion constraints during generation. Experiments across diverse constraint settings demonstrate the effectiveness of our framework.
