• During training, physically plausible ground-truth motions (m_gt ) are intentionally distorted using vertical bias and temporal smoothing to create artifact-laden motions (m_d ​). DMC learns to recover refined motions (m_r​) from distorted motions (m_d )​, conditioned on the original textual description.

• At inference time, DMC is applied as a post-hoc refinement step to motions generated by any pre-trained text-to-motion model (m_gen​ ).

• Without modifying the original generation pipeline, DMC corrects physical artifacts (e.g., foot skating, floating, clipping and ground penetration), producing refined motions (m_r ​) that are both physically plausible and semantically consistent.

Generating semantically aligned human motion from textual descriptions has made rapid progress, but ensuring both semantic and physical realism in motion remains a challenge. In this paper, we introduce the Distortion-aware Motion Calibrator (DMC), a post-hoc module that refines physically implausible motions (e.g., foot floating) while preserving semantic consistency with the original textual description. Rather than relying on complex physical modeling, we propose a self-supervised and data-driven approach, whereby DMC learns to obtain physically plausible motions when an intentionally distorted motion and the original textual descriptions are given as inputs. We evaluate DMC as a post-hoc module to improve motions obtained from various text-to-motion generation models and demonstrate its effectiveness in improving physical plausibility while enhancing semantic consistency. The experimental results show that DMC reduces FID score by 42.74% on T2M and 13.20% on T2M-GPT, while also achieving the highest R-Precision. When applied to high-quality models like MoMask, DMC improves the physical plausibility of motions by reducing penetration by 33.0% as well as adjusting floating artifacts closer to the ground-truth reference. These results highlight that DMC can serve as a promising post-hoc motion refinement framework for any kind of text-to-motion models by incorporating textual semantics and physical plausibility.

@inproceedings{

}