Metraipolis › archive › dc_16b11ea77a68

Repurposing RGB-based Foundation Model for Depth Estimation on Thermal Images Using Hierarchical Supervision — arXiv:2608.11564

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11564
License (as archived)
CC0-1.0
Archived
2026-10-19T05:49:20.999Z
SHA-256 of the archived text
61f42158b22f7275c6153418ac44fa31a73df3f620bc6cb49d278a9f2942834b
Stable URL of this page
https://metraipolis.com/documento/dc_16b11ea77a68

How to cite

Repurposing RGB-based Foundation Model for Depth Estimation on Thermal Images Using Hierarchical Supervision — arXiv:2608.11564 — arXiv (en), https://arxiv.org/abs/2608.11564 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_16b11ea77a68 (Metraipolis archive dc_16b11ea77a68, sha256 61f42158b22f7275c6153418ac44fa31a73df3f620bc6cb49d278a9f2942834b)
BibTeX
@misc{dc16b11ea77a68,
  title = {Repurposing RGB-based Foundation Model for Depth Estimation on Thermal Images Using Hierarchical Supervision — arXiv:2608.11564},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11564},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_16b11ea77a68; sha256 61f42158b22f7275c6153418ac44fa31a73df3f620bc6cb49d278a9f2942834b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11564. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Depth estimation from thermal images is highly valuable for robotic applications in adverse conditions, such as nighttime and rainy weather. Recent studies have sought to transfer knowledge from RGB-based foundation models to thermal modalities, yet the rich hierarchical representations these models encode remain underutilized. To address this limitation, we propose RGB-HS, a novel framework for thermal-image depth estimation that leverages hierarchical supervision from an RGB-based foundation model. Specifically, we first replace the baseline thermal encoder with a foundational model and introduce a parallel RGB branch that also employs a foundational model as an encoder of the same architecture, taking RGB images as input. The alignment is then performed across multiple levels between the tokens of the two encoders, allowing the thermal student branch to capture both structural precision and semantic abstraction from the RGB teacher branch. Furthermore, we introduce verification to refine the alignment process by weighting tokens from the RGB branch based on RGB image quality. Extensive experiments on the popular benchmark demonstrate that RGB-HS achieves competitive performance and more effectively exploits the representational capacity of RGB-based foundation models for depth estimation on thermal images.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.11564 — 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 2026-10-19T05:42:25.866Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).