Bruno Figueiredo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Bruno Figueiredo has a total of 73 co-authors. Here are the top co-authors by number of shared publications:
- Paulo Jorge Sousa Cruz
University of Minho
20 shared publications - Filipe Brandão
University of Minho
10 shared publications - Francisca Aroso
University of Minho
6 shared publications - Rui Reis
University of Minho
6 shared publications - Aires Camões
University of Minho
5 shared publications - António Morais
School of Architecture, Art and Design; Lab2PT - Landscapes, Heritage and Territory Laboratory, EAAD - University of Minho, Guimarães, Portugal
4 shared publications
Latest Publications
- 6 November 2026
- Published by Taylor & Francis in The Design Journal
- p. 1-30
Design for additive manufacturing. The application to the AEC industry
- 6 November 2026
- Published by Taylor & Francis in The Design Journal
- p. 1-30
Design for additive manufacturing. The application to the AEC industry
- Open Access
- 7 October 2026
- Published by Springer Nature
- p. 1252-1260
Digitising Waste: Teaching Circular Construction Through Computational Workflows and Digital Fabrication
- 7 October 2026
- Published by Springer Nature
- p. 1252-1260
Open AccessDigitising Waste: Teaching Circular Construction Through Computational Workflows and Digital Fabrication
- 10 August 2026
- Published by Springer Nature in Construction Robotics
- Vol. 10 (2) , 43
Hybrid additive–subtractive 3D concrete printing via ultrasonic robotic excision for interlocking component fabrication
- 10 August 2026
- Published by Springer Nature in Construction Robotics
- Vol. 10 (2) , 43
Hybrid additive–subtractive 3D concrete printing via ultrasonic robotic excision for interlocking component fabrication
- Open Access
- 25 June 2026
- Published by University of Porto
AI-ASSISTED 2D-3D SEMANTIC SEGMENTATION FOR STONE LEVEL HBIM
The Scan-to-HBIM process plays a central role in documenting heritage buildings by converting unstructured reality-capture data into semantically enriched BIM models. However, automating this conversion remains challenging, particularly for historic structures with complex and irregular stone masonry. This paper investigates the use of Convolutional Neural Networks (CNNs) to support the segmentation of photogrammetry-derived point clouds from Romanesque stone masonry, aiming to automate the data-processing stage of Scan-to-HBIM workflows. A dual 2D–3D pipeline is proposed in which high-resolution façade images are segmented using U-Net and the Segment Anything Model (SAM) to identify stone blocks, mortar joints, and openings. In this framework, U-Net is trained to classify point-cloud data into defined masonry-related classes, while SAM is employed either to generate training masks for U-Net or to directly project selected segmentations onto the 3D point cloud. The workflow enables the creation of a model capable of automatically segmenting point-cloud data and assigning semantic attributes to specific classes. Applied to a Romanesque church in Portugal, the approach shows that AI can reliably detect primary masonry components and reduce the labour required for detailed classification, although challenges persist in fine-grained stone delineation and model generalisation across diverse datasets. Overall, the study demonstrates a complementary dual-CNN strategy with strong potential to support the generation of high-detail HBIM models.
- 25 June 2026
- Published by University of Porto
Open AccessAI-ASSISTED 2D-3D SEMANTIC SEGMENTATION FOR STONE LEVEL HBIM
The Scan-to-HBIM process plays a central role in documenting heritage buildings by converting unstructured reality-capture data into semantically enriched BIM models. However, automating this conversion remains challenging, particularly for historic structures with complex and irregular stone masonry. This paper investigates the use of Convolutional Neural Networks (CNNs) to support the segmentation of photogrammetry-derived point clouds from Romanesque stone masonry, aiming to automate the data-processing stage of Scan-to-HBIM workflows. A dual 2D–3D pipeline is proposed in which high-resolution façade images are segmented using U-Net and the Segment Anything Model (SAM) to identify stone blocks, mortar joints, and openings. In this framework, U-Net is trained to classify point-cloud data into defined masonry-related classes, while SAM is employed either to generate training masks for U-Net or to directly project selected segmentations onto the 3D point cloud. The workflow enables the creation of a model capable of automatically segmenting point-cloud data and assigning semantic attributes to specific classes. Applied to a Romanesque church in Portugal, the approach shows that AI can reliably detect primary masonry components and reduce the labour required for detailed classification, although challenges persist in fine-grained stone delineation and model generalisation across diverse datasets. Overall, the study demonstrates a complementary dual-CNN strategy with strong potential to support the generation of high-detail HBIM models.
- Open Access
- 25 June 2026
- Published by University of Porto
MANAGEMENT OF THE DESIGN KNOWLEDGE CORE IN A CROSS-PLATFORM ENVIRONMENT OF THE BIM PROJECT
Effective project data management and consistent communication throughout the project lifecycle are key aspects of BIM. Nevertheless, in current BIM practices, despite rapid advances across the board and in automating specific tasks, design knowledge remains fragmented across files, platforms, and disciplines, limiting its validation and the reuse of design rules. In particular, it becomes a vital issue during iterative design handover among stakeholders. Addressing the limitations above, this paper proposes a framework for management of the shared knowledge core, transposing multimodal architectural knowledge - textual requirements, parametric definitions, and semantic rules - into a unified, object-oriented data model integrated with a BIM environment. By shifting from file-based exchanges to object-level communication, the framework enables automated validation of design intent and the reuse of knowledge datasets. Through a plan-layout case study, the results show how abstract knowledge can be integrated into the BIM lifecycle to enhance coordination and facilitate maturity in the AEC industry.
- 25 June 2026
- Published by University of Porto
Open AccessMANAGEMENT OF THE DESIGN KNOWLEDGE CORE IN A CROSS-PLATFORM ENVIRONMENT OF THE BIM PROJECT
Effective project data management and consistent communication throughout the project lifecycle are key aspects of BIM. Nevertheless, in current BIM practices, despite rapid advances across the board and in automating specific tasks, design knowledge remains fragmented across files, platforms, and disciplines, limiting its validation and the reuse of design rules. In particular, it becomes a vital issue during iterative design handover among stakeholders. Addressing the limitations above, this paper proposes a framework for management of the shared knowledge core, transposing multimodal architectural knowledge - textual requirements, parametric definitions, and semantic rules - into a unified, object-oriented data model integrated with a BIM environment. By shifting from file-based exchanges to object-level communication, the framework enables automated validation of design intent and the reuse of knowledge datasets. Through a plan-layout case study, the results show how abstract knowledge can be integrated into the BIM lifecycle to enhance coordination and facilitate maturity in the AEC industry.
- Open Access
Carbonation and Chloride Attack in 3D-Printed Cementitious Materials: A Systematic Durability Review
3D Concrete Printing (3DCP) is increasingly explored as a digital fabrication technology offering design freedom, automation, and material efficiency. Nevertheless, its application in reinforced and long-life structures remains limited by insufficient understanding and poor comparability of durability performance, as previous reviews have not systematically linked methodologies to transport-related results. This study presents a systematic and critical review of carbonation and chloride ingress in 3DCP cementitious materials, conducted in accordance with the PRISMA methodology. Following a structured database search and two-stage screening process, the selected studies are subjected to qualitative analysis. Experimental methodologies, specimen typologies, exposure conditions, and attack directions are compiled and qualitatively compared. The review highlights pronounced methodological heterogeneity and frequent under-reporting of key parameters, particularly attack direction, sealing conditions, CO2 concentration, and indicator methods, limiting cross-study comparison. Despite these limitations, consistent qualitative trends are identified. Printed specimens generally exhibit inferior durability performance than cast specimens, while cold joints are associated with increased penetration depth and result dispersion. Directional effects are non-negligible, although they are systematically addressed in only a limited number of studies. Overall, the findings emphasise the critical role of process-induced features and the need for harmonised testing methods to enable reliable durability assessment.
Open AccessCarbonation and Chloride Attack in 3D-Printed Cementitious Materials: A Systematic Durability Review
3D Concrete Printing (3DCP) is increasingly explored as a digital fabrication technology offering design freedom, automation, and material efficiency. Nevertheless, its application in reinforced and long-life structures remains limited by insufficient understanding and poor comparability of durability performance, as previous reviews have not systematically linked methodologies to transport-related results. This study presents a systematic and critical review of carbonation and chloride ingress in 3DCP cementitious materials, conducted in accordance with the PRISMA methodology. Following a structured database search and two-stage screening process, the selected studies are subjected to qualitative analysis. Experimental methodologies, specimen typologies, exposure conditions, and attack directions are compiled and qualitatively compared. The review highlights pronounced methodological heterogeneity and frequent under-reporting of key parameters, particularly attack direction, sealing conditions, CO2 concentration, and indicator methods, limiting cross-study comparison. Despite these limitations, consistent qualitative trends are identified. Printed specimens generally exhibit inferior durability performance than cast specimens, while cold joints are associated with increased penetration depth and result dispersion. Directional effects are non-negligible, although they are systematically addressed in only a limited number of studies. Overall, the findings emphasise the critical role of process-induced features and the need for harmonised testing methods to enable reliable durability assessment.
- 2 January 2026
- Published by Springer Nature
- p. 423-431
Improving Natural Ventilation Through 3D Concrete Printing
- 2 January 2026
- Published by Springer Nature
- p. 423-431
Improving Natural Ventilation Through 3D Concrete Printing
- 2 January 2026
- Published by Springer Nature
- p. 557-564
A Systematic Review on the Durability of 3D-Printed Cementitious Materials: Insights and Research Challenges
- 2 January 2026
- Published by Springer Nature
- p. 557-564
A Systematic Review on the Durability of 3D-Printed Cementitious Materials: Insights and Research Challenges