We present HumanCM, a one-step human motion prediction framework built upon consistency models. Instead of relying on multi-step denoising as in diffusion-based methods, HumanCM performs efficient single-step generation by learning a self-consistent mapping between noisy and clean motion states. The framework adopts a Transformer-based spatiotemporal architecture with temporal embeddings to model long-range dependencies and preserve motion coherence. Experiments on Human3.6M and HumanEva-I demonstrate that HumanCM achieves comparable or superior accuracy to state-of-the-art diffusion models while reducing inference steps by up to two orders of magnitude.
@article{arxiv.2510.16709,
title = {HumanCM: One Step Human Motion Prediction},
author = {Liu Haojie and Gao Suixiang},
journal= {arXiv preprint arXiv:2510.16709},
year = {2025}
}