3D reconstruction of building interiors based on scan-to-BIM and generative design for as-built building

Cai, W.; Hua, D.; Li, S.; Xue, S. and Xu, Z. (2026) 3D reconstruction of building interiors based on scan-to-BIM and generative design for as-built building. Engineering, Construction and Architectural Management, 33(3), pp. 1959-1979. ISSN 0969-9988

Abstract

Purpose – BIM technology has a huge potential for improving the renovation efficiency for as-built buildings. However, due to the absence of raw design drawings and the complex interior environment, it is difficult to implement 3D reconstruction of building interiors in interior renovation projects. Therefore, this study proposes a 3D reconstruction framework of building interiors, with an aim to generate building interiors building information modeling (BIM) models quickly and accurately based on scan-to-BIM and generative design. Design/methodology/approach – The proposed framework begins by reconstructing interior structured elements based on the scan-to-BIM process including collecting accurate information of as-built buildings by laser scanning, obtaining point clouds of structured elements through deep learning and developing an efficient dynamo algorithm workflow for generating structured elements BIM model. For unstructured elements, intelligent layout design and efficient BIM generation are conducted by combining the BIM tools and generative design. Findings – The successful implementation of the proposed framework in a conference room demonstrated the feasibility of the proposed framework. The semantic segmentation scheme based on deep learning also exhibited excellent recognition and high efficiency for interior structured elements. Furthermore, it is proved that the combination of scan-to-BIM and generative design has high application value in the 3D reconstruction of building interiors. Originality/value – On one hand, a feasible framework is proposed to generate BIM model of building interiors, improve interoperability among different software tools, streamline the complexity of the scan-to-BIM process and meet the reconfiguration requirement of unstructured elements layout scheme in interior renovation projects. On the other hand, the use of BIM and various emerging technologies can drive digital transformation and further advance the industrialization process of interior renovation in as-built buildings.

Item Type: Article
Uncontrolled Keywords: 3D reconstruction; building interiors; generative design; scan-to-BIM
Index terms: emerging technology, renovation, interoperability, implementation, efficiency, reconstruction, building information modelling, transformation, deep learning, conference, design drawing, building interior, reconfiguration, laser scanning, methodology, complexity, generative design, workflow, point cloud, industrialization
Subjects: performance management, management, renovation and retrofit, information systems, systems and processes, systems engineering, business, artificial intelligence, technical documentation, design process, digital design, research methods, economic development, building construction, specialized design, organization, research dissemination and communication, analytical methods, innovation and technology management, contractual arrangements
Topics: Engineering Principles, Procurement, Sustainability, Quality Management, Research Practice, Business Strategy, Design Practice, Digital Applications
Descriptive scope: 3 PCT

N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here