Cumincad : CUMINCAD Papers : Search Results

CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 20 of 185

Reformat results as: short short into frame detailed detailed into frame

_id	sigradi2023_312
id	sigradi2023_312
authors	Buzó, Raúl and Armagno, Ángel
year	2023
title	Application of Artificial Intelligence in the Acquisition of Architectural Forms.
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 773–782
summary	The primary objective of this research was to explore the effectiveness of Neural Radiance Fields (NeRF) in acquiring architectural forms and compare them with traditional photogrammetry results. The study began with a comprehensive literature review on AI in architecture and NeRF. Afterwards, a single case study applicable to both NeRF and photogrammetry was selected for comparison. The NeRF model showed the ability to accurately represent details and light effects, adapting reflections and transparencies to real-world conditions, as well as handling occlusions, and inferring three-dimensional information. In similar situations, Photogrammetry generated less coherent volumetrics or failed to interpret objects. Additionally, tests with a reduced number of images showed that the NeRF model maintained its characteristics, while photogrammetry suffered a decrease in quality and completeness. However, NeRF's performance was influenced by data collection quality. Insufficient data led to lower-quality volumetrics with imperfections, highlighting the importance of careful data collection, even with technologies like NeRF.
keywords	Neural Radiance Fields (NeRF), Photogrammetry, Artificial intelligence, Design, Architecture
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	acadia23_v2_420
id	acadia23_v2_420
authors	Guida, George; Escobar, Daniel; Navarro, Carlos
year	2023
title	3D Neural Synthesis: Gaining Control with Neural Radiance Fields
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 2: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-0-3]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 420-428.
summary	This research introduces a novel, 3D machine-learning, aided design approach for early design stages. Integrating language within a multimodal framework grants designers greater control and agency in generating 3D forms. The proposed method leverages Stable Diffusion and Runway's Gen1 through the generation of 3D Neural Radiance Fields (NeRFs), surpassing the limitations of 2D image-based outcomes in aiding the design process. This paper presents a flexible machine-learning workflow taught to students in a conference workshop, and outlines the multimodal methods used - between text, image, video, and NeRFs. The resultant NeRF design outcomes are contextualized within a Unity agent-based, virtual environment for architectural simulation, and are expe- rienced with real-time VFX augmentations. This hybridized design process ultimately highlights the importance of feedback loops and control within machine-learning, aided-design processes.
series	ACADIA
type	paper
email
last changed	2024/12/20 09:12

_id	acadia23_v3_185
id	acadia23_v3_185
authors	Zhang, Haotian
year	2023
title	Today Once More: Filmmaking with Photogrammetry and Neural Radiance Fields
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 3: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-1-0]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 24-32.
summary	Photogrammetry and Neural Radiance Fields (NeRF) are volumetric capture methods that enable high-fidelity documentation of spatial and chromatic details of existing environments. These methods, alternative to canonical architectural drawing as characterized by the abundance of textural data, offer a new realm of representation that could potentially shift our perception of the city. This workshop searched for their medium specificities, particularly addressing the gap between faithful reference to the real world and speculation in the digital realm, while harnessing the tension in between. This workshop introduced the two techniques and relevant tools in the context of filmmaking, providing tutorials on NVidia Instant-ngp (NeRF), COLMAP, RealityCapture (photogrammetry), and Blender (point cloud manipulation). It unpacked the tools to understand their mechanisms and capabilities, ultimately working toward collective films about Hong Kong. In our exploration, we analyzed the mediums to use them critically. This analysis examined the unique qualities of each medium in two ways – by assessing its capacity and identifying its constraints. The capacities and constraints set it apart from other mediums or reality, the gap between which manifests the inherent characteristic yet to be aestheticized.
series	ACADIA
type	workshop
email
last changed	2024/04/17 14:00

_id	architectural_intelligence2023_20
id	architectural_intelligence2023_20
authors	Mojtaba Pourbakht & Yoshihiro Kametani
year	2023
title	Distance estimation technique from 360-degree images in built-in environments
doi	https://doi.org/https://doi.org/10.1007/s44223-023-00039-8
source	Architectural Intelligence Journal
summary	The present study introduces a novel approach for quantifying distances within constructed environments. A mathematical model was developed for distance estimation in image processing using width and height estimation. In order to determine distance, the study employed the use of visual angle and sky view factor (SVF). Additionally, a camera with capabilities similar to the human eye was utilized to capture 360-degree photographs from a fixed position within a virtual reality corridor. The technique of Sky View Factor (SVF) is employed in indoor environments with ceilings by eliminating windows, doors, and roofs, thereby simulating a virtual sky. This enables the calculation of various parameters such as the image's area, area fraction, and aspect ratio through the utilization of image processing methods. Distance estimation can be predicted through the utilization of the sky view factor and visual angle, employing a linear regression analysis. The method of virtual sky view factor (VSVF) has potential applications in the fields of Engineering, robotics, and architecture for the estimation of indoor distances.
series	Architectural Intelligence
email
last changed	2025/01/09 15:03

_id	cdrf2023_102
id	cdrf2023_102
authors	Alberto Fernandez González, Nikoletta Karastathi
year	2023
title	Threading Cellular Architecture Geometries
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_9
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
summary	In the massive computer architecture known as cellular automata (CA), finite-state machines, also known as finite-state automata, are arranged in a discontinuous network that permits local interactions between neighbors. As self-organizing artificial systems, such as neural networks and genetic algorithms, developed from vast systems formed with essential elements and just local interactions, CA is mainly related to artificial intelligence (AI) (a seed interacts with its own neighbors, which are usually just the cells closer to the seed as an activator). In order to produce architectural spaces of various sizes, this research develops digital experiments that analyze the interactions between environmental conditions as input, CA as generator/propagator, and geometrical emergent patterns from knitting and weaving processes as translators/mediators. This method functions as a bottom-up strategy in which information from the environment can influence the activation and deactivation of rules, theoretically fostering a reprogrammable structure that can evolve.
series	cdrf
email
last changed	2024/05/29 14:04

_id	ecaade2023_328
id	ecaade2023_328
authors	Andreou, Alexis, Kontovourkis, Odysseas, Solomou, Solon and Savvides, Andreas
year	2023
title	Rethinking Architectural Design Process using Integrated Parametric Design and Machine Learning Principles
doi	https://doi.org/10.52842/conf.ecaade.2023.2.461
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 461–470
summary	Artificial Intelligence (AI) has the potential to process vast amounts of subjective and conflicting information in architecture. However, it has mostly been used as a tool for managing information rather than as a means of enhancing the creative design process. This work proposes an innovative way to enhance the architectural design process by incorporating Machine Learning (ML), a type of Artificial Intelligence (AI), into a parametric architectural design process. ML would act as a mediator between the architects' inputs and the end-users' needs. The objective of this work is to explore how Machine Learning (ML) can be utilized to visualize creative designs by transforming information from one form to another - for instance, from text to image or image to 3D architectural shapes. Additionally, the aim is to develop a process that can generate comprehensive conceptual shapes through a request in the form of an image and/or text. The suggested method essentially involves the following steps: Model creation, Revisualization, Performance evaluation. By utilizing this process, end-users can participate in the design process without negatively affecting the quality of the final product. However, the focus of this approach is not to create a final, fully-realized product, but rather to utilize abstraction and processing to generate a more understandable outcome. In the future, the algorithm will be improved and customized to produce more relevant and specific results, depending on the preferences of end-users and the input of architects.
keywords	End-users, Architects, Mass personalization, Visual programming, Neural Network Algorithm
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_44
id	ecaade2023_44
authors	Mayrhofer-Hufnagl, Ingrid and Ennemoser, Benjamin
year	2023
title	From Linear to Manifold Interpolation: Exemplifying the paradigm shift through interpolation
doi	https://doi.org/10.52842/conf.ecaade.2023.2.419
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 419–429
summary	The advent of artificial intelligence, specifically neural networks, has marked a significant turning point in the field of computation. During such transformative times, we are often faced with a dearth of appropriate vocabulary, which forces us to rely on existing terms, regardless of their inadequacy. This paper argues that the term “interpolation,” typically used in deep learning (DL), is a prime example of this phenomenon. It is not uncommon for beginners to misunderstand its meaning, as DL pioneer Francois Chollet (2017) has noted. This misreading is especially true in the discipline of architecture, and this study aims to demonstrate how the meaning of “interpolation” has evolved in the second digital turn. We begin by illustrating, using 2D data, the difference between linear interpolation in the context of topological figures and its use in DL algorithms. We then demonstrate how 3DGANs can be employed to interpolate across different topologies in complex 3D space, highlighting the distinction between linear and manifold interpolation. In both 2D and 3D examples, our results indicate that the process does not involve continuous morphing but instead resembles the piecing together of a jigsaw puzzle to form many parts of a larger ambient space. Our study reveals how previous architectural research on DL has employed the term “interpolation” without clarifying the crucial differences from its use in the first digital turn. We demonstrate the new possibilities that manifold interpolation offers for architecture, which extend well beyond parametric variations of the same topology.
keywords	Interpolation, 3D Generative Adversarial Networks, Deep Learning, Hybrid Space
series	eCAADe
email
last changed	2023/12/10 10:49

_id	sigradi2023_20
id	sigradi2023_20
authors	Yonder, Veli Mustafa, Çavka, Hasan Burak and Dogan, Fehmi
year	2023
title	A Case Study on Architectural Sketch Recognition Utilizing Deep Learning Networks for Exterior and Interior Datasets
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 265–276
summary	Sketching is a pivotal component in facilitating the effective conveyance of ideas and the actualization of architectural design concepts. The potential applications of machine learning and computer vision algorithms in the fields of technical drawing and architectural graphic communication are substantial, presenting a diverse array of possibilities. This research investigates the effectiveness of deep learning-based classification techniques in analyzing both indoor and outdoor freehand architectural perspective drawings. Furthermore, the transfer learning approach was employed in this binary classification problem. The primary aim of this study is to train deep neural networks to recognize and interpret freehand architectural perspective drawings effectively and precisely. In this context, pre-trained models such as GoogLeNet, ResNet-50, AlexNet, ResNet-101, Places365-GoogLeNet, and DarkNet-53 were fine-tuned. The findings indicate that the ResNet-101 architecture has significant levels of validation accuracy, yet the validation accuracy of the Places365-GoogLeNet and AlexNet pretrained models is comparatively lower.
keywords	Machine Learning, Transfer Learning, Drawing Recognition, Deep Neural Nets, Image Classification
series	SIGraDi
email
last changed	2024/03/08 14:06

_id	ecaade2023_10
id	ecaade2023_10
authors	Sepúlveda, Abel, Eslamirad, Nasim and De Luca, Francesco
year	2023
title	Machine Learning Approach versus Prediction Formulas to Design Healthy Dwellings in a Cold Climate
doi	https://doi.org/10.52842/conf.ecaade.2023.2.359
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 359–368
summary	This paper presents a study about the prediction accuracy of daylight provision and overheating levels in dwellings when considering different methods (machine learning vs prediction formulas), training, and validation data sets. An existing high-rise building located in Tallinn, Estonia was considered to compare the best ML predictive method with novel prediction formulas. The quantification of daylight provision was conducted according to the European daylight standard EN 17037:2018 (based on minimum Daylight Factor (minDF)) and overheating level in terms of the degree-hour (DH) metric included in local regulations. The features included in the dataset are the minDF and DH values related to different combinations of design parameters: window-to-floor ratio, level of obstruction, g-value, and visible transmittance of the glazing system. Different training and validation data sets were obtained from a main data set of 5120 minDF values and 40960 DH values obtained through simulation with Radiance and EnergyPlus, respectively. For each combination of training and validation dataset, the accuracy of the ML model was quantified and compared with the accuracy of the prediction formulas. According to our results, the ML model could provide more accurate minDF/DH predictions than by using the prediction formulas for the same design parameters. However, the amount of room combinations needed to train the machine-learning model is larger than for the calibration of the prediction formulas. The paper discuss in detail the method to use in practice, depending on time and accuracy concerns.
keywords	Optimization, Daylight, Thermal Comfort, Overheating, Machine Learning, Predictive Model, Dwellings, Cold Climates
series	eCAADe
email
last changed	2023/12/10 10:49

_id	acadia23_v2_104
id	acadia23_v2_104
authors	Brandiæ Lipiñska, Monika; Dade-Robertson, Martyn; Zhang, Meng
year	2023
title	Space Architecture, Biotechnology, and Parametric Processes: Design through Assembly, Growth, and Fabrication Parameters in an Iterative Feedback Loop
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 2: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-0-3]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 104-115.
summary	Resource scarcity in extraterrestrial environments, like the Moon or Mars, imposes limitations on construction, necessitating resource and energy optimization. To respond to these challenges, this paper explores the development of a parametric framework, bridging the fields of space architecture, biotechnology, and parametric processes, allowing for the development of energy and resource-efficient structural components. The foundation for the framework is built upon ongoing research conducted in collabo- ration with NASA Ames Research Center, focusing on a mycelium-based aggregation of Martian regolith for construction. Due to the nature of the material and targeted environ- ment, the proposed parametrization process is based on specific assembly, growth, and fabrication requirements. The framework incorporates a feedback loop between design, computational simulation, and physical testing. The interaction of multiple systems, imple- mented through an iterative process and hybrid design approaches, enable continuous design refinement. These systems incorporate inputs from the interconnected disciplines that pose challenges when evaluated separately. The paper recognizes the challenge of identifying crucial parameters and implicit actions, and bridging the gap between theory and implementation. It calls for further work on programming the parametrization frame- work, and integrating computational simulations and data evaluation. In emphasizing the interdisciplinary nature of future space exploration and architecture, this paper under- scores the significance of integrating diverse disciplines and technologies.
series	ACADIA
type	paper
email
last changed	2024/12/20 09:12

_id	caadria2023_244
id	caadria2023_244
authors	Cutellic, Pierre
year	2023
title	An Inverse Modeling Method to Estimate Uncertain Spatial Configurations From 2D Information and Time-Based Visual Discriminations
doi	https://doi.org/10.52842/conf.caadria.2023.1.261
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 261–270
summary	This paper focuses on a specific aspect of human visual discrimination from computationally generated solutions for CAAD ends. The bottleneck at work here concern informational ratios of discriminative rates over generative ones. The amount of information that can be brought to a particular sensory modality for human perception is subject to bandwidth and dimensional limitations. This problem is well known in Brain-Computer Interfaces, where the flow of relevant information must be maintained through such interaction for applicative ends and adoption of use in many fields of human activity. While architectural modeling conveys a high level of complexity in its processes, let alone in the presentation of its generated design solutions, promises in applicative potentials of such interfaces must be made aware of these fundamental issues and need developments of appropriate sophistication. This paper addresses this informational bottleneck by introducing a method to retrieve spatial information from the rapid serial visual presentation of generated pictures. This method will be explained and defined as inverse modeling, based on inverse graphics, and its relation to human visual processing.
keywords	Neurodesign, Design Computing and Cognition, Brain-Computer Interfaces, Generative Design, Computer Vision
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	acadia23_v3_99
id	acadia23_v3_99
authors	Decq, Odile
year	2023
title	Design Excellence Award
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 3: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-1-0]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 24-32.
summary	In a society where all productions tend to insidiously become uniform, ignoring any cultural particularism, historical or social, the philosophy of Studio Odile Decq (the Studio) has always been to be specific and particular. By questioning the command, the use, the matter, the body, the technique, and the taste, the invented architecture offers a paradoxical look, at the same time tender and severe, on our world. In a creative and positive work process, the obstacles are always transformed into advantages, all while developing a specific image for each project with the most advanced contemporary technologies. On the occasion of the realization of numerous architectural projects, the Studio has also often developed the interior fittings and the furniture, in a continuity of thought and in relation with needs, each time different and specific. The Studio’s work is a complete universe, in which architecture, design, art and urbanism come together, challenge each other, and respond to each other. The direct style of Odile Decq is matched by her architecture, with bold geometries and innovative creations. In the same continuity, the Studio interfaces with industrial companies, in fields as daiverse as lighting, acoustics, glazing, and furniture design, responding each time to special technical requirements. The conceptual process, centered around experimentation, is closely followed by Odile Decq herself. Thus, the design includes, from the start all the parameters to succeed, in an initially iterative approach, to arrive at a perfectly integrated project.
series	ACADIA
type	award
email
last changed	2024/04/17 13:59

_id	ecaade2023_15
id	ecaade2023_15
authors	Heyik, Muhammet Ali, Karataº, Emre and Erdogan, Meral
year	2023
title	Leveraging Collective Intelligence from Crowdsourcing to Co-creation in Field Studies
doi	https://doi.org/10.52842/conf.ecaade.2023.1.129
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 1, Graz, 20-22 September 2023, pp. 129–138
summary	The paper explores the advantages and forms of harnessing collective intelligence (CI) that can support cognition, coordination, and collaboration in architectural education. These forms focus on various design tasks by enhancing groups’ performance, bringing together diverse actors within a distributed network, and strengthening the process through informed and inclusive decisions. Specifically, we propose a co-creation strategy to comprehensively map place values and rapidly scan the field. By incorporating the technical requirements and contextual constraints of various fields, we conducted iterative workshops within the action research circle. The results show that the CI approach yields significantly positive impacts, justifying its application through a functional triple structure that replaces individually challenging and frustrating fieldwork. This structure involves: (1) definition of parameters and tasks for groups based on objectives, (2) the collection and extraction of values from the field, and (3) the creation of collective cartographies. Additionally, our research makes a valuable contribution by providing a theoretical framework for diverse forms of CI, highlighting the advantages of crowdsourcing-based platforms in both urban and rural contexts, and evaluating the usability of tested mobile apps. We conclude the paper by discussing the limitations, adaptabilities, and potentials for the broader use of CI in the field studies of students.
keywords	Collective Intelligence, Co-creation, Field Study
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2023_178
id	caadria2023_178
authors	Mathur, Praneet
year	2023
title	Creative Impact of an Event-Driven Visual Scripting Tool
doi	https://doi.org/10.52842/conf.caadria.2023.2.331
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 331–340
summary	Computational design is gaining global prominence. With the increase in demand for technologically capable designers, we find more designers understanding computers better, learning programming languages and adapting technologies to fit their needs. This has led to multidisciplinary communities forming around visual scripting tools (VSTs) like Grasshopper3D, Dynamo, etc. These communities consist of many users from creative fields who find it easier to learn a visual scripting language than a programming language. However, function-driven programming and various quirks of these tools delimit their application to a closed spectrum of use-cases. This further limits the users’ capabilities and forces many to hack their way around basic programming language paradigms like loops, event handling, etc. VSTs seem to promote a creative affinity to programming, while also making it more approachable and accessible. To understand the creative impact of a more powerful VST, this paper outlines the development and use of an agnostic event-driven VST - one based on MVVM software architecture and linked list data structures, written entirely in C# (WPF) with minimal dependencies. With features like plugin extensibility and interoperability with 3D software (e.g., Rhinoceros), this new tool is built to aid creative programming driven by events and data. This implies enhanced capabilities for the user and enables interactive computation of data in real-time. User experience inferences are derived from diverse user studies, with a focus on students and professionals in the design and AEC industries. Various parameters and test scenarios are used to objectively assess the impact of enabling event-driven programming for creative use.
keywords	Event-Driven Programming, Visual Programming, Computational Design Tools
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	caadria2023_43
id	caadria2023_43
authors	Onishi, Ryo, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year	2023
title	Remote Sharing System for 3D Real Objects with Point Cloud Reconstruction Using Deep Learning Point Cloud Completion
doi	https://doi.org/10.52842/conf.caadria.2023.2.381
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 381–390
summary	Currently, teleconferencing via the internet is widely used in society. However, physical models such as design study models, which are often used in face-to-face meetings in the fields of architecture and urban design, cannot be shared in teleconferences where information is shared on a display. Telepresence is a technology for sharing 3D real objects at a distance that gives the sensation of sharing and experiencing the environment and objects at a remote location. As one such technology, a system has been developed in which the point cloud of a real object acquired by a camera is divided into objects by instance segmentation, and the divided point cloud is transmitted to the remote user, who can manipulate it on mixed reality. There is a problem of missing point clouds in areas not seen by the RGB-D camera, such as occlusion and the back of the camera. This research aims to develop a system that can remotely manipulate point clouds with more accurate geometry by using a point cloud completion technique based on deep learning to complement missing point clouds. This system is expected to contribute to smoother teleconferencing of remote participants.
keywords	Remote meeting, Real-time sharing, Three-dimensional remote sharing, Mixed Reality, Point cloud completion
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	sigradi2023_277
id	sigradi2023_277
authors	Retamal, Martin and Loyola, Mauricio
year	2023
title	Enhancing Spatial Skills and Blueprint Reading in Construction Workers with Low-Cost Virtual Reality Equipment
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 473–482
summary	This study examines the application of virtual reality (VR) in remote education for construction trades, specifically focusing on the development of specialized skills and the ability to interpret blueprints. An experiment was conducted that empirically compared the spatial comprehension and blueprint reading abilities of two groups of workers. These workers used both high-end and low-end VR equipment to visualize construction spaces and blueprints. The findings reveal high levels of spatial comprehension and blueprint interpretation without significant differences between the two types of equipment. Overall, the participants responded positively to the experience. The research concludes that VR may serve as an efficient and accessible tool for training in construction fields, with low-end equipment providing a cost-effective and practical solution.
keywords	Virtual Reality, Construction Education, Spatial Skills
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	sigradi2023_437
id	sigradi2023_437
authors	Hernández Vargas, José
year	2023
title	Spatially Graded Modeling: An Integrated Workflow For 3D Concrete Printing
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 361–372
summary	While 3D concrete printing (3DCP) has surged in popularity, methods to harness its design potential remain largely underdeveloped. Existing design-to-manufacture workflows most commonly restrict the design to the overall geometry and a set of print parameters that may fall outside of the scope of the designer. This study presents a novel approach to integrate design and manufacturing by an integrated design-to-manufacture workflow that allows the gradation of the wall thickness along the printed part, which can be independently manipulated using established computer graphic techniques like texture projection and mesh coloring. The effectiveness of this workflow is demonstrated through the fabrication of a test body featuring a customized surface pattern. This approach aims to extend the design scope for 3DCP, enabling the addition and editing of surface patterns without geometry or code manipulation.
keywords	Robotic fabrication, 3D concrete printing, Variable filament width, Design for manufacturing, Print path design
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	sigradi2023_196
id	sigradi2023_196
authors	Houang Daher, Cassio and Coeli Ruschel, Regina
year	2023
title	Clustering metamodel for predictive performance for dynamic shading facade
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 447–459
summary	Dynamic shading facades present a challenge for the computational simulation of illuminance performance in the project's design phase. Such architectural elements have conflicting functions: shading without blocking natural light. The evaluation of these dynamic elements depends on multiple parameters and combinations, which results in higher complexity in compositions and difficulty in understanding. The objective is to identify the optimized positioning of dynamic elements of the facade; still in the early stages of the project, to have good illuminance performance for all busy hours of the year. The research conducted here is experimental, using computer simulation. Our model considers as the dependent variable the average annual illuminance. The independent variables analyzed are shoebox orientation, positioning of the fins, date, and time. The contribution of this research is to test the set of results of the independent variables by training an algorithm capable of replacing the simulation.
keywords	Machine Learning, Metamodel, Dynamic Facade, Performance Evaluation, Clustering
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	cdrf2023_454
id	cdrf2023_454
authors	Wei Ye, Yingzhou Gao, Weiguo Xu
year	2023
title	A Parametric Wave Joint for Robotic Fabrication of Digital Stereotomy
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_38
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
summary	This paper explores the potential of digital stereotomy in combination with robotic fabrication to increase the precision and complexity of stone processing. To enable the application of these techniques in outdoor environments, modular joints designed for robotic assembly are necessary. Additionally, the cutting process must be efficient and minimize material waste. To address these challenges, this research proposes a parametric wave joint design that enables rapid cutting and straightforward assembly by a robotic system. The joint contains motion space allowing it to slide into accurate assembly position, enabling the robot to complete the assembly without requiring highly precise vision or gripper in outdoor situations. Furthermore, the wave joint design eliminates the need for milling, reducing the processing time. The paper presents a robotic arm-cutting method for this joint and conducts experiments using foam and robotic arm hot-wire cutting to simulate stone cutting. The feasibility of the joint is tested through the assembly of a bent column, and finite element analysis is used to compare the stresses on two joint parts under shear force with different control parameters. The study confirms the feasibility of the wave joint design for robotic assembly and the efficiency of robotic arm cutting. The findings may inform the development of modular assemblies for robotic systems in stone processing applications.
series	cdrf
email
last changed	2024/05/29 14:04

_id	ecaade2023_25
id	ecaade2023_25
authors	Weissenböck, Renate and Werner, Jan Michael
year	2023
title	Analogue Computation: An educational framework for introducing first-year architecture students to parametric design through manual making
doi	https://doi.org/10.52842/conf.ecaade.2023.1.011
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 1, Graz, 20-22 September 2023, pp. 11–20
summary	This paper describes an educational framework for introducing first-year architecture students to concepts of parametric design through manual making, without the use of digital tools. Responding to shifts in our current society and culture, the authors developed a new curriculum for the first-year-course “Architectural and Artistic Design” at the FH JOANNEUM University of Applied Sciences and refined it over the last three years. The intention was to prepare students to their highly digitized future careers in architecture, by focusing on the thinking process, the major aspect of parametric design. The didactic concept of using analog tools reacts to the digital saturation of Generation Z students, and the post-digital re-awareness of physical and material aspects. Students engaged in a series of small tasks in open-ended “design through making” processes, applying parametric concepts for experimental form finding. The course assignment was to design a modular spatial structure, based on adjustable parameters of module geometry, connection strategy, and assembly logic. The results were assessed through student feedback and demonstrate the educational and creative value of this pedagogical approach and indicate that the students improved their understanding of parametric design as a thinking process beyond current technologies.
keywords	Analogue Computation, Parametric Design, Parametric Thinking, Design Through Making, Manual Making, Modular Structures, Design Education
series	eCAADe
email
last changed	2023/12/10 10:49

For more results click below: