IKMo: Image-Keyframed Motion Generation with Trajectory-Pose Conditioned Motion Diffusion Model
IKMo generates high-fidelity human motion using a diffusion model by decoupling trajectory and pose constraints. It uses a two-stage parallel control strategy to refine inputs and then fuse trajectory and keyframe pose information into the generation process. This method successfully handles conflicting spatial constraints from user trajectories and image poses, setting a new state-of-the-art.