Luigi Piccinelli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Luigi Piccinelli has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Christos Sakaridis
ETH Zurich, Zurich, Switzerland
1 shared publication - Denys Rozumnyi
Meta Reality Labs Zurich
1 shared publication - Hermann Blum
University of Bonn
1 shared publication Johannes Schönberger
Meta Reality Labs Zurich
1 shared publication- Luc Van Gool
INSAIT, Sofia University “St. Kliment Ohridski
1 shared publication - Marc Pollefeys
ETH Zurich
1 shared publication
Latest Publications
- 9 September 2026
- Published by Springer Nature
- p. 414-432
Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs
- 9 September 2026
- Published by Springer Nature
- p. 414-432
Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs
- Top Cited Papers
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 2354-2367
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler
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.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 2354-2367
Top Cited PapersUniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler
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.