Metraipolis › archive › dc_2bf8477aa026

FlowMoDE: Coarse-to-fine Flow Matching for Detail-aware Sim-to-Real Monocular Depth Estimation — arXiv:2610.41190

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41190
License (as archived): CC0-1.0
Archived: 2026-11-03T08:20:27.791Z
SHA-256 of the archived text: 45b1f51c269492083313691aa05e33ce48108a35dea45d08fb416d876047ceb4
Stable URL of this page: https://metraipolis.com/documento/dc_2bf8477aa026

How to cite

FlowMoDE: Coarse-to-fine Flow Matching for Detail-aware Sim-to-Real Monocular Depth Estimation — arXiv:2610.41190 — arXiv (en), https://arxiv.org/abs/2610.41190 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bf8477aa026 (Metraipolis archive dc_2bf8477aa026, sha256 45b1f51c269492083313691aa05e33ce48108a35dea45d08fb416d876047ceb4)

BibTeX

@misc{dc2bf8477aa026,
  title = {FlowMoDE: Coarse-to-fine Flow Matching for Detail-aware Sim-to-Real Monocular Depth Estimation — arXiv:2610.41190},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41190},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bf8477aa026; sha256 45b1f51c269492083313691aa05e33ce48108a35dea45d08fb416d876047ceb4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41190. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Monocular depth estimation is a fundamental capability for 3D spatial perception in robotic and intelligent systems. While data-driven discriminative methods have achieved compelling performance for monocular depth estimation, generative approaches can reconstruct fine structural details with stronger generalization. However, most existing generative diffusion models suffer from low inference efficiency caused by multi-step sampling, whereas single-step diffusion models struggle to recover high-fidelity depth maps. To mitigate these drawbacks, this paper presents FlowMoDE, a coarse-to-fine flow-matching-based framework for efficient, structure-aware monocular depth estimation supporting sim-to-real and cross-scene generalization. The core architecture first conducts coarse-level decoding conditioned on diffused features extracted from a pre-trained semantic encoder, and subsequently restores fine-grained structural patterns via expanded decoding layers. Trained exclusively on a single synthetic indoor dataset, our proposed method outperforms prior methods across five real-world indoor and outdoor datasets, yielding an average 14.1% reduction in relative error against state-of-the-art works as well as 9.9\% reduction in chamfer distance for point cloud reconstruction. We further validate the generalization capability of FlowMoDE on realistic robotic scenes, with qualitative comparisons against state-of-the-art methods. The project page is 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/2610.41190 — 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 2026-11-03T08:06:38.821Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).