id |
acadia23_v2_606 |
authors |
Pinochet, Diego |
year |
2023 |
title |
Deciphering Design Sketches As 3D Models: A Sequence -2- Sequence Approach to Generative Modeling Using Sketches |
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 606-615. |
summary |
In this paper, I present a human-machine, collaborative, 3D modeling system that combines human gestures with generative 3D modeling. The project seeks to explore the unfolding of design ideas while reframing the concept of design workflows, knowledge encapsulation, disembodiment, and representation in 3D CAD processes. Using machine learning and interactive computation, this project links user sketches to generative 3D modeling using a sequence-to-sequence model. By encapsulating expert knowledge related to 3D modeling, this project seeks to eliminate intermediate representations, such as, sections, elevations, and floorplans, in the design process to engender immediate, real-time, 3D model generation from hand sketches (Figure 1). Whereas, most of the projects using generative machine learning to produce 3D models focus on the one-to-one fidelity between sketches and 3D models, this research focuses on the generative power of gesture sequences to generate novel 3D models. This experiment aims to answer, among others, the following questions: Can the use of machine learning reframe the generation of 3D models in a more embodied way? Is it possible to capture design inten- tions from sketches to generate 3D shapes using machine learning? Can we design and explore ideas inside a computer without representing them, but focusing on the unique sequences that originate novel designs? |
series |
ACADIA |
type |
paper |
email |
|
full text |
file.pdf (2,979,790 bytes) |
references |
Content-type: text/plain
|
Angel Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese et al (2015)
Shapenet: An information-rich 3d model repository
, arXiv preprint arXiv:1512.0301
|
|
|
|
Ben Poole, Ajay Jain, Jonathan T. Barron, and Ben Mildenhall (2022)
Dreamfusion: Text-to-3d using 2d diffusion
, arXiv preprint arXiv:2209.14988
|
|
|
|
Chen-Hsuan Lin, Jun Gao, Luming Tang, Towaki Takikawa, Xiaohui Zeng, Xun Huang, Karsten Kreis, Sanja Fidler, Ming-Yu Liu, and Tsung-Yi Lin (2023)
Magic3d: High-resolution text-to-3d content creation
, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 300-309
|
|
|
|
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna (2016)
Rethinking the inception architecture for computer vision
, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2818-2826
|
|
|
|
Christopher B. Choy, Danfei Xu, JunYoung Gwak, Kevin Chen, and Silvio Savarese (2016)
3d-r2n2: A unified approach for single and multi-view 3d object reconstruction
, Computer Vision– ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII 14, pp. 628-644. Springer International Publishing, 2016
|
|
|
|
Diego Pinochet (2016)
Antithetical Colloquy
, ACADIA // 2016: POSTHUMAN FRONTIERS: Data, Designers, and Cognitive Machines [Proceedings of the 36th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-77095-5] Ann Arbor 27-29 October, 2016, pp. 402-411
|
|
|
|
Gómez Pérez (2012)
The Historical Context of Contemporary Architectural Representation
, Persistent Modelling: Extending the Role of Architectural Representation edited by Phil Ayres (London and New York: Routledge, 2012)
|
|
|
|
Hallam Elizabeth and Tim Ingold (2007)
Creativity and Cultural Improvisation
, Oxford: Berg
|
|
|
|
Immanuel Koh (2020)
Artificial & Architectural Intelligence in Design
, Architecture and Sustainable Design, Singapore University of Technology and Design
|
|
|
|
Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, and Josh Tenenbaum (2016)
Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling
, Advances in neural information processing systems 29
|
|
|
|
Marian Kleineberg, Matthias Fey, and Frank Weichert (2020)
Adversarial generation of continuous implicit shape representations
, arXiv preprint arXiv:2002.00349
|
|
|
|
Mateusz Zwierzycki (2020)
On AI Adoption Issues in Architectural Design Identifying the issues based on an extensive literature review
, eCAADe 2020: Anthropologic : Architecture and Fabrication in the cognitive age
|
|
|
|
Mengtian Li, Zhe Lin, Radomir Mech, Ersin Yumer, and Deva Ramanan (2019)
Photo-sketching: Inferring contour drawings from images
, 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1403-1412
|
|
|
|
Sebastian Lunz, Yingzhen Li, Andrew Fitzgibbon, and Nate Kushman (2020)
Inverse graphics gan: Learning to generate 3d shapes from unstructured 2d data
, arXiv preprint arXiv:2002.12674
|
|
|
|
last changed |
2024/12/20 09:13 |
|