FoVA-Depth: Field-of-View Agnostic Depth Estimation for Cross-Dataset Generalization
Wide field-of-view (FoV) cameras efficiently capture large portions of the scene, which makes them attractive in multiple domains, such as automotive and robotics. For such applications, estimating depth from multiple images is a critical task, and therefore, a large amount of ground truth (GT) data...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Wide field-of-view (FoV) cameras efficiently capture large portions of the
scene, which makes them attractive in multiple domains, such as automotive and
robotics. For such applications, estimating depth from multiple images is a
critical task, and therefore, a large amount of ground truth (GT) data is
available. Unfortunately, most of the GT data is for pinhole cameras, making it
impossible to properly train depth estimation models for large-FoV cameras. We
propose the first method to train a stereo depth estimation model on the widely
available pinhole data, and to generalize it to data captured with larger FoVs.
Our intuition is simple: We warp the training data to a canonical, large-FoV
representation and augment it to allow a single network to reason about diverse
types of distortions that otherwise would prevent generalization. We show
strong generalization ability of our approach on both indoor and outdoor
datasets, which was not possible with previous methods. |
---|---|
DOI: | 10.48550/arxiv.2401.13786 |