Saved in:
Bibliographic Details
Main Authors: Sombekke, Niels, Wijnhoven, Rob G. J., Oswald, Martin R.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.26381
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914602326949888
author Sombekke, Niels
Wijnhoven, Rob G. J.
Oswald, Martin R.
author_facet Sombekke, Niels
Wijnhoven, Rob G. J.
Oswald, Martin R.
contents We present a multi-modal classification framework that fuses satellite and street-level imagery through a Perceiver IO architecture operating on spatial patch tokens from a shared DINOv2 backbone. The design naturally handles a variable number of street-level views per building without padding or fixed-size pooling, and jointly predicts multi-label roof element and roof material classes. We construct a large-scale dataset of 32,135 buildings (61,672 segments) spanning ten countries, pairing satellite images with up to eight street-level views per segment and evaluating four masking strategies for isolating the target building. We propose an RGB-M masking strategy that appends the building footprint mask as a fourth input channel, providing a soft spatial prior that outperforms hard cropping across both modalities. The Perceiver IO fusion model improves over all other fusion strategies and yields substantial per-class gains for attributes visible from street level (e.g., +11.3 AP for slate, +1.3 AP for dormers), though the satellite-only baseline retains a slight advantage in macro-averaged mAP for classes that are predominantly visible from above. These results establish a scalable, flexible architecture for multi-modal building inspection that can accommodate heterogeneous inputs and multiple output tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26381
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Modal Building Inspection via Perceiver IO Fusion of Satellite and Street-Level Imagery
Sombekke, Niels
Wijnhoven, Rob G. J.
Oswald, Martin R.
Computer Vision and Pattern Recognition
We present a multi-modal classification framework that fuses satellite and street-level imagery through a Perceiver IO architecture operating on spatial patch tokens from a shared DINOv2 backbone. The design naturally handles a variable number of street-level views per building without padding or fixed-size pooling, and jointly predicts multi-label roof element and roof material classes. We construct a large-scale dataset of 32,135 buildings (61,672 segments) spanning ten countries, pairing satellite images with up to eight street-level views per segment and evaluating four masking strategies for isolating the target building. We propose an RGB-M masking strategy that appends the building footprint mask as a fourth input channel, providing a soft spatial prior that outperforms hard cropping across both modalities. The Perceiver IO fusion model improves over all other fusion strategies and yields substantial per-class gains for attributes visible from street level (e.g., +11.3 AP for slate, +1.3 AP for dormers), though the satellite-only baseline retains a slight advantage in macro-averaged mAP for classes that are predominantly visible from above. These results establish a scalable, flexible architecture for multi-modal building inspection that can accommodate heterogeneous inputs and multiple output tasks.
title Multi-Modal Building Inspection via Perceiver IO Fusion of Satellite and Street-Level Imagery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.26381