Visual Estimation of Building Condition with Patch-level ConvNets

TL;DR

This paper introduces a novel vision-based method using multi-scale patch-level convolutional neural networks to objectively estimate building condition from exterior images, serving as a proxy for subjective appraiser assessments.

Contribution

The paper presents a new patch-level CNN approach for building condition estimation, reducing subjectivity and improving objectivity in real estate valuation.

Findings

Visual estimates correlate well with appraiser assessments

Patch-based CNNs effectively capture building condition features

Method provides a scalable, automated assessment tool

Abstract

The condition of a building is an important factor for real estate valuation. Currently, the estimation of condition is determined by real estate appraisers which makes it subjective to a certain degree. We propose a novel vision-based approach for the assessment of the building condition from exterior views of the building. To this end, we develop a multi-scale patch-based pattern extraction approach and combine it with convolutional neural networks to estimate building condition from visual clues. Our evaluation shows that visually estimated building condition can serve as a proxy for condition estimates by appraisers.