Metraipolis › archive › dc_ae38cb951eb3

PhysibleMDM: Enforcing Inference-Time Physical Feasibility Constraints on Motion Diffusion Models via Noise Optimization — arXiv:2610.30500

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.30500
License (as archived): CC0-1.0
Archived: 2026-10-25T08:34:23.631Z
SHA-256 of the archived text: f8ab06eb43e5a716656b670a814a55f7389f4bab524e1b584c810532c9a0cce8
Stable URL of this page: https://metraipolis.com/documento/dc_ae38cb951eb3

How to cite

PhysibleMDM: Enforcing Inference-Time Physical Feasibility Constraints on Motion Diffusion Models via Noise Optimization — arXiv:2610.30500 — arXiv (en), https://arxiv.org/abs/2610.30500 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae38cb951eb3 (Metraipolis archive dc_ae38cb951eb3, sha256 f8ab06eb43e5a716656b670a814a55f7389f4bab524e1b584c810532c9a0cce8)

BibTeX

@misc{dcae38cb951eb3,
  title = {PhysibleMDM: Enforcing Inference-Time Physical Feasibility Constraints on Motion Diffusion Models via Noise Optimization — arXiv:2610.30500},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30500},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae38cb951eb3; sha256 f8ab06eb43e5a716656b670a814a55f7389f4bab524e1b584c810532c9a0cce8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30500. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Motion Diffusion Models (MDMs) can generate diverse and visually appealing human motion; yet, the resulting trajectories frequently violate physical constraints, limiting their downstream use in simulation and control. We present PhysibleMDM, a framework that promotes physical feasibility of MDM output by optimizing at inference time the diffusion noise without retraining the generative model. We introduce a set of surrogate feasibility constraints that can be evaluated without full trajectory simulation. These constraints combine kinematic checks (e.g., ground penetration, slip, and self-collision) with dynamic feasibility tests computed via an inverse-dynamics inner loop formulated as a cone program. We solve the resulting black-box noise optimization problem using the Separable Covariance Matrix Adaptation Evolution Strategy (Sep-CMA-ES), thereby avoiding reliance on computationally expensive and discontinuous gradients. An autoregressive scheme then chains optimized segments to synthesize long motion sequences. Across 100 motion styles on an SMPL humanoid, PhysibleMDM reduces mean ground penetration, self-collision penetration, and ground slip by 75%, 92%, and 74%, respectively, relative to unoptimized diffusion output. Across 11 sequences for a custom bipedal robot, it achieves median reductions of 89.5% in per-sequence mean acceleration-reconstruction error and 79.5% in the mean inverse-dynamics residual.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.30500 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-25T08:31:13.158Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).