Go to CVPR 2025 Workshop HuMoGen homepageGoal-Driven Human Motion Synthesis in Diverse Tasks
Keywords: Human Motion Synthesis, Goal-driven Motion Synthesis
Abstract: We propose a framework for goal-driven human motion generation, which can synthesize interaction-rich scenarios. Given the goal positions for key joints, our pipeline automatically generates natural full-body motion that approaches the target in cluttered environments. Our pipeline solves the complex constraints in a tractable formulation by disentangling the process of motion generation into two stages. The first stage computes the trajectory of the key joints like hands and feet to encourage the character to naturally approach the target position while avoiding possible physical violation. We demonstrate that diffusion-based guidance sampling can flexibly adapt to the local scene context while satisfying goal conditions. Then the subsequent second stage can easily generate plausible full-body motion that traverses the key joint trajectories. The proposed pipeline applies to various scenarios that have to concurrently account for 3D scene geometry and body joint configurations.
Supplementary Material: zip
Submission Number: 12
Loading