EUVIMEDEUVIMED entdecken
Crossref

UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler

Luigi Piccinelli, Christos Sakaridis, Yung-Hsu Yang, Mattia Segu, Siyuan Li, Wim Abbeloos, Luc Van Gool

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-03 · 48 (3) · 2354-2367

DOI: 10.1109/tpami.2025.3628473 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-03. Verfasst von Luigi Piccinelli und 6 weiteren Autor:innen. Die Arbeit wurde bisher 93-mal zitiert (Crossref) und nennt 88 Literaturangaben. Gefördert von: Toyota Motor Europe.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate monocular metric depth estimation (MMDE) is crucial to solving downstream tasks in 3D perception and modeling. However, the remarkable accuracy of recent MMDE methods is confined to their training domains. These methods fail to generalize to unseen domains even in the presence of moderate domain gaps, which hinders their practical applicability. We propose a new model, UniDepthV2, capable of reconstructing metric 3D scenes from solely single images across domains. Departing from the existing MMDE paradigm, UniDepthV2 directly predicts metric 3D points from the input image at inference time without any additional information, striving for a universal and flexible MMDE solution. In particular, UniDepthV2 implements a self-promptable camera module predicting a dense camera representation to condition depth features. Our model exploits a pseudo-spherical output representation, which disentangles the camera and depth representations. In addition, we propose a geometric invariance loss that promotes the invariance of camera-prompted depth features. UniDepthV2 improves its predecessor UniDepth model via a new edge-guided loss which enhances the localization and sharpness of edges in the metric depth outputs, a revisited, simplified and more efficient architectural design, and an additional uncertainty-level output which enables downstream tasks requiring confidence. Thorough evaluations on ten depth datasets in a zero-shot regime consistently demonstrate the superior performance and generalization of UniDepthV2. Code and models are available at: github.com/lpiccinelli-eth/UniDepth.

Förderung

  • Toyota Motor Europe

Zitieren

APA

Piccinelli, L., Sakaridis, C., Yang, Y. H., Segu, M., Li, S., Abbeloos, W., & Van Gool, L. (2026). UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(3), 2354-2367. https://doi.org/10.1109/tpami.2025.3628473

Vancouver

Piccinelli L, Sakaridis C, Yang YH, Segu M, Li S, Abbeloos W, et al. UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(3):2354-2367. doi:10.1109/tpami.2025.3628473

BibTeX
@article{Piccinelli2026,
  author = {Piccinelli, Luigi and Sakaridis, Christos and Yang, Yung-Hsu and Segu, Mattia and Li, Siyuan and Abbeloos, Wim and Van Gool, Luc},
  title = {UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {3},
  pages = {2354--2367},
  doi = {10.1109/tpami.2025.3628473}
}
Kostenlos starten →