Metraipolis › archive › dc_fb11988447ef

PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation — arXiv:2610.08068

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.08068
License (as archived): CC0-1.0
Archived: 2026-10-07T13:07:27.937Z
SHA-256 of the archived text: 28e6b798ccec9ca53ebb1afae876c0e33b196c40e20130c6547888130fbac4f3
Stable URL of this page: https://metraipolis.com/documento/dc_fb11988447ef

How to cite

PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation — arXiv:2610.08068 — arXiv (en), https://arxiv.org/abs/2610.08068 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb11988447ef (Metraipolis archive dc_fb11988447ef, sha256 28e6b798ccec9ca53ebb1afae876c0e33b196c40e20130c6547888130fbac4f3)

BibTeX

@misc{dcfb11988447ef,
  title = {PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation — arXiv:2610.08068},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08068},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb11988447ef; sha256 28e6b798ccec9ca53ebb1afae876c0e33b196c40e20130c6547888130fbac4f3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08068. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Realistic physical interaction is a cornerstone of embodied intelligence, yet collecting paired visual--tactile data remains costly. Visual-to-tactile synthesis offers a promising approach to augmenting such data, but learning this mapping is complicated by the gap between visual appearance and contact-related material properties, as well as spatial misalignment in paired observations. To address these challenges, we present \textbf{PhysTacGen}, a visual-to-optical-tactile image generation framework that integrates material-aware descriptions with geometric conditioning. First, we introduce Group Tactile Policy Optimization (GTPO), a reinforcement learning strategy that refines a vision--language model to generate structured material descriptions using task-specific rewards. Second, we combine DINOv2-based pair curation with monocular relative-depth estimation to select training pairs and provide geometric priors. Finally, an SDXL ControlNet synthesizes optical tactile images conditioned on RGB, relative depth, and GTPO-generated text. Experiments on curated SSVTP data demonstrate improved structural similarity over the compared baselines, while a blinded user study shows a preference for GTPO-generated descriptions. Generated tactile inputs also improve performance on an attribute-derived force-coefficient prediction proxy. Together, these results demonstrate the effectiveness of PhysTacGen for optical tactile image synthesis and its utility in the evaluated downstream this http URL code will be available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.08068 — 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 2026-10-07T12:37:32.944Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).