SketchOpt: Sketch-based Parametric Model Retrieval for Generative Design

Keshavarzi, Mohammad; Hotson, Clayton; Cheng, Chin-Yi; Nourbakhsh, Mehdi; Bergin, Michael H.; Rahmani, Amir M.

doi:10.1145/3411763.3451620

Cited by 7 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Turrin et al [9] discussed the benefits of combining parametric modeling with genetic algorithms (GAs) to achieve performance-oriented processes in design. Keshavarzi et al [10] used hand drawn floor plans and annotations as inputs and outputted a fully parameterized vectorized model in real-time. Unlu et al [11] proposed the idea of using multiple neural networks to predict different parameter sets that must be correlated.…”

Section: Parametric Modelingmentioning

confidence: 99%

A Spline Based Parametric Modeling Method for Ladder like Facilities

Zhu,

He,

Liu

et al. 2023

FCIS

View full text Add to dashboard Cite

Existing modeling methods for modeling ladder like facilities are often limited to a single technical means and require a large amount of user input or guidance. To address the above issues, we propose a spline based parametric modeling method for modeling general complex ladder like facilities. Firstly, a facility framework spline generation method was improved to provide an editable initial framework. In addition, the method for calculating the position of contour points is improved, and the surface mesh of the facility is generated by combining contour curve constraint algorithms that meet various dimensions and geometric constraints that control the shape. Finally, a profile mesh generation algorithm was designed to achieve mesh generation of contour surfaces. The experimental results show that this method can be used to model different types of ladders like facilities. Compared with existing methods, facility framework spline generation and component surface mesh generation can significantly improve the efficiency of model generation.

show abstract

Section: Parametric Modelingmentioning

confidence: 99%

A Spline Based Parametric Modeling Method for Ladder like Facilities

Zhu,

He,

Liu

et al. 2023

FCIS

View full text Add to dashboard Cite

show abstract

“…Generative Design (GD) has rapidly emerged as a powerful Artificial Intelligence (AI) enhanced design paradigm enabling human experts (e.g. architects) to augment their creativity and accelerate the design processes by suggesting new ideas and improving design quality in co-creation [1,2,3].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Intelligence Approach to Training Generative Design Assistants: Partnership Between Human Experts and AI Enhanced Co-Creative Tools

Mao

Rafner

Wang

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

The emergence of generative design (GD) has introduced a new paradigm for co-creation between human experts and AI systems. Empirical findings have shown promising outcomes such as augmented human cognition and highly creative design products. Barriers still remain that prevent individuals from perceiving and adopting AI, entering into collaboration with AI and sustaining it over time. It is even more challenging for creative design industries to adopt and trust AI where these professionals value individual style and expression, and therefore require highly personalized and specialized AI assistance. In this paper, we present a holistic hybrid intelligence (HI) approach for individual experts to train and personalize their GD assistants on the fly. Our contribution to human-AI interaction is three-fold including i) a programmable common language between human and AI to represent the expert’s design goals to the generative algorithm, ii) a human-centered continual training loop to seamlessly integrate AI-training into the expert’s task workflow, iii) a hybrid intelligence narrative to address the psychological willingness to spend time and effort training such a virtual assistant. This integral approach enables individuals to directly communicate design goals to AI and seeks to create a psychologically safe space for adopting, training and improving AI without the fear of job-replacement. We concertize these constructs through a newly developed Hybrid Intelligence Technology Acceptance Model (HI-TAM). We used mixed methods to empirically evaluate this approach through the lens of HI-TAM with 8 architectural professionals working individually with a GD assistant to co-create floor plan layouts of office buildings. We believe that the proposed approach enables individual professionals, even non-technical ones, to adopt and trust AI-enhanced co-creative tools.

show abstract

“…In addition, sketch-guided topology optimization functionality has been integrated in several commercial software. SketchOpt [7] introduces an automated design generation system that takes as input a sketch of the basic plane and as output a parametric model prepared for multi-objective building optimization. It helps designers explore multiple performance-based layout plans in the early stages of the design process.…”

Section: Introductionmentioning

confidence: 99%

Sketch driven machine-learning based topology optimization

Wang,

Zhang,

Youn

et al.

Proceedings of the Sixth International Conference On Soft Computing, Machine Learning and Optimisation in Civil, Structural And

View full text Add to dashboard Cite

Sketch design plays a very important role in model design. In order to improve the efficiency of existing design models that rely on computer-aided and human experience guidance, this work proposes a sketch driven machine-learning based topology optimization method. It helps designers directly design hand-drawn sketches to obtain topology-optimized structures that conform to sketching experience. The proposed method uses neural style transfer technique, and can compensate for the lack of design experience to obtain optimized structures without the need of multiple computational simulation interactions. Specific structural shapes and design styles according to the design requirements also can be obtained. In contrast to the approach of specifying the undesignable domain and initial layout, similarity constraints between sketches and structures are constructed to quantify the degree of inheritance of different sketches. Both 2D and 3D problems are solved to illustrate the effectiveness of the proposed approach.

show abstract

SketchOpt: Sketch-based Parametric Model Retrieval for Generative Design

Cited by 7 publications

References 31 publications

A Spline Based Parametric Modeling Method for Ladder like Facilities

A Spline Based Parametric Modeling Method for Ladder like Facilities

A Hybrid Intelligence Approach to Training Generative Design Assistants: Partnership Between Human Experts and AI Enhanced Co-Creative Tools

Sketch driven machine-learning based topology optimization

Contact Info

Product

Resources

About