Learning local depth regression from defocus blur by soft-assignment encoding

We present a novel, to the best of our knowledge, patch-based approach for depth regression from defocus blur. Most state-of-the-art methods for depth from defocus (DFD) use a patch classification approach among a set of potential defocus blurs related to a depth, which induces errors due to the con...

Full description

Saved in:
Bibliographic Details
Published in:Applied optics (2004) 2022-10, Vol.61 (29), p.8843
Main Authors: Leroy, Rémy, Trouvé-Peloux, Pauline, Le Saux, Bertrand, Buat, Benjamin, Champagnat, Frédéric
Format: Article
Language:English
Subjects:
Computer Science
Datasets
Engineering Sciences
Image classification
Mathematics
Physics
Regression
Statistical analysis
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a novel, to the best of our knowledge, patch-based approach for depth regression from defocus blur. Most state-of-the-art methods for depth from defocus (DFD) use a patch classification approach among a set of potential defocus blurs related to a depth, which induces errors due to the continuous variation of the depth. Here, we propose to adapt a simple classification model using a soft-assignment encoding of the true depth into a membership probability vector during training and a regression scale to predict intermediate depth values. Our method uses no blur model or scene model; it only requires a training dataset of image patches (either raw, gray scale, or RGB) and their corresponding depth label. We show that our method outperforms both classification and direct regression on simulated images from structured or natural texture datasets, and on raw real data having optical aberrations from an active DFD experiment.
ISSN:1559-128X
2155-3165
DOI:10.1364/AO.471105