Metraipolis › archive › dc_a6691bc9dd86
CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation — arXiv:2609.21455
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.21455
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T02:29:32.689Z
- SHA-256 of the archived text
738890eb834d6dfc7e6d764cd72135f3f5a29d3aafffa969073ace347336e9b9- Stable URL of this page
https://metraipolis.com/documento/dc_a6691bc9dd86
How to cite
CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation — arXiv:2609.21455 — arXiv (en), https://arxiv.org/abs/2609.21455 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6691bc9dd86 (Metraipolis archive dc_a6691bc9dd86, sha256 738890eb834d6dfc7e6d764cd72135f3f5a29d3aafffa969073ace347336e9b9)
BibTeX
@misc{dca6691bc9dd86,
title = {CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation — arXiv:2609.21455},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.21455},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6691bc9dd86; sha256 738890eb834d6dfc7e6d764cd72135f3f5a29d3aafffa969073ace347336e9b9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21455. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While diffusion-based text-to-video (T2V) models have demonstrated impressive capability in generating realistic and temporally coherent videos, they often fail to respect fundamental physical dynamics. Although recent physics-constrained methods incorporate explicit dynamics priors to improve physical plausibility, they remain limited to simple single-type motions, depend on manually specified parameters, and struggle to generalize to unseen physical laws. In this work, we propose CompAdapt, a physics-consistent T2V framework for adaptable generation across complex real-world scenarios. It extends neural dynamics modeling beyond single-type motions to encompass composite physical behaviors, including coupled motions, multi-stage transitions, and multi-object collisions. Furthermore, CompAdapt translates natural language prompts into structured physical semantics, enabling end-to-end specification of motion types, temporal relations, and initial physical parameters. To generalize to novel physical environments, CompAdapt introduces dynamics-aware prior matching, achieving one-shot adaptation without retraining the core dynamics module. In addition, a physics-aware latent feature fusion module improves visual fidelity under fast and complex motion. Experiments on physics-focused T2V benchmarks demonstrate that CompAdapt improves physical consistency over both general T2V models and physics-constrained baselines, while preserving high visual quality and adaptability to unseen dynamics. The project page is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.21455 — 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 2026-10-10T02:07:36.059Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).