Saved in:
Bibliographic Details
Main Authors: Versteeg, Luuk, Wijnhoven, Rob G. J., Oswald, Martin R.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.26370
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911717885214720
author Versteeg, Luuk
Wijnhoven, Rob G. J.
Oswald, Martin R.
author_facet Versteeg, Luuk
Wijnhoven, Rob G. J.
Oswald, Martin R.
contents We present a method for jointly predicting instance-level roof segment masks together with three continuous geometric attributes -- building height, roof slope, and roof azimuth -- from a single aerial orthophoto. Our approach extends Mask R-CNN with a dedicated attribute regression branch and introduces two key innovations: a conditional azimuth loss that suppresses supervision for flat roof segments where azimuth labels are inherently noisy, and a log-normalized height representation that addresses the heavily skewed distribution of building heights. We train and evaluate on a large-scale dataset of Dutch aerial images paired with automatically derived ground truth from 3DBAG, a nationwide LiDAR-based 3D building dataset. Using a DINOv3 ConvNeXt-Base backbone, our method achieves a mean absolute error of approximately 4 degrees for roof slope, 7 degrees for azimuth, and 1 meter for building height, with an instance segmentation AP$_{50}$ of 0.566. The predicted per-segment masks and attributes are sufficient to reconstruct simplified 3D building models (LoD2) from a single overhead image, requiring expensive 3D reference data only for training.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26370
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Joint Instance Segmentation and Geometric Attribute Regression for Roof Structures in Aerial Imagery
Versteeg, Luuk
Wijnhoven, Rob G. J.
Oswald, Martin R.
Computer Vision and Pattern Recognition
We present a method for jointly predicting instance-level roof segment masks together with three continuous geometric attributes -- building height, roof slope, and roof azimuth -- from a single aerial orthophoto. Our approach extends Mask R-CNN with a dedicated attribute regression branch and introduces two key innovations: a conditional azimuth loss that suppresses supervision for flat roof segments where azimuth labels are inherently noisy, and a log-normalized height representation that addresses the heavily skewed distribution of building heights. We train and evaluate on a large-scale dataset of Dutch aerial images paired with automatically derived ground truth from 3DBAG, a nationwide LiDAR-based 3D building dataset. Using a DINOv3 ConvNeXt-Base backbone, our method achieves a mean absolute error of approximately 4 degrees for roof slope, 7 degrees for azimuth, and 1 meter for building height, with an instance segmentation AP$_{50}$ of 0.566. The predicted per-segment masks and attributes are sufficient to reconstruct simplified 3D building models (LoD2) from a single overhead image, requiring expensive 3D reference data only for training.
title Joint Instance Segmentation and Geometric Attribute Regression for Roof Structures in Aerial Imagery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.26370