Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization

TL;DR

This paper introduces a retrieval-guided diffusion noise optimization method for generating human motion under highly constrained, complex spatiotemporal conditions, enabling more controllable virtual agent behaviors.

Contribution

It proposes a training-free, retrieval-guided approach with relational task parsing and reward-guided initialization to handle challenging motion constraints.

Findings

Successfully generates human motion with severe spatial obstacles.

Handles specified walking steps and complex constraints effectively.

Leverages large motion datasets and LLM for improved reasoning and guidance.

Abstract

Generating human motion that satisfies customized zero-shot goal functions, enabling applications such as controllable character animation and behavior synthesis for virtual agents, is a critical capability. While current approaches handle many unseen constraints, they fail on tasks with very challenging spatiotemporal restrictions, such as severe spatial obstacles or specified numbers of walking steps. To equip motion generators for these highly constrained tasks, we present a retrieval-guided method built on the training-free diffusion noise optimization framework. The key idea is to search within large motion datasets for guidance that can potentially satisfy difficult constraints. We introduce relational task parsing to group target constraints and identify the difficult ones to be handled by retrieved reference. A better initialization for diffusion noise is then obtained via a reward-guided mask that combines random noise with retrieved noise. By optimizing diffusion noise from this improved initialization, we successfully solve highly constrained generation tasks. By leveraging LLM for relational task parsing, the whole framework is further enabled to automatically reason for what to retrieve, improving the intelligence of moving agents under a training-free optimization scheme.