Style2Fab: Functionality-Aware Segmentation for Fabricating Personalized 3D Models with Generative AI

Faruqi, Faraz; Katary, Ahmed; Hasic, Tarik; Abdel-Rahman, Amira; Rahman, Nayeemur; Tejedor, Leandra; Leake, Mackenzie; Hofmann, Megan; Mueller, Stefanie

doi:10.1145/3586183.3606723

Cited by 6 publications

(3 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A designer could utilize this tool, which is called Style2Fab, to personalize 3D models of objects using only natural language prompts to describe their desired design. The user could then fabricate the objects with a 3D printer [99]. It is only a matter of time until AI tools will support doctors in 3D designing, personalization and improving efficiency of individualized appliances for biocompatible 3D printing.…”

Section: Discussionmentioning

confidence: 99%

The Evolution of Robin Sequence Treatment Based on the Biomimetic Interdisciplinary Approach: A Historical Review

Čverha,

Varga,

Trenčanská

et al. 2023

Biomimetics

View full text Add to dashboard Cite

The Robin sequence is a congenital anomaly characterized by a triad of features: micrognathia, glossoptosis, and airway obstruction. This comprehensive historical review maps the evolution of approaches and appliances for its treatment from the past to the current modern possibilities of an interdisciplinary combination of modern engineering, medicine, materials, and computer science combined approach with emphasis on designing appliances inspired by nature and individual human anatomy. Current biomimetic designs are clinically applied, resulting in appliances that are more efficient, comfortable, sustainable, and safer than legacy traditional designs. This review maps the treatment modalities that have been used for patients with a Robin sequence over the years. Early management of the Robin sequence focused primarily on airway maintenance and feeding support, while current management strategies involve both nonsurgical and surgical interventions and biomimetic biocompatible personalized appliances. The goal of this paper was to provide a review of the evolution of management strategies for patients with the Robin sequence that led to the current interdisciplinary biomimetic approaches impacting the future of Robin Sequence treatment with biomimetics at the forefront.

show abstract

Section: Discussionmentioning

confidence: 99%

The Evolution of Robin Sequence Treatment Based on the Biomimetic Interdisciplinary Approach: A Historical Review

Čverha,

Varga,

Trenčanská

et al. 2023

Biomimetics

View full text Add to dashboard Cite

show abstract

“…In the wake of strikingly realistic randomly generated 2D images [ 1 , 2 ], there is a mounting expectation for generative models to replicate the same success when automatically synthesizing 3D objects. Demand for such models arises in various domains, ranging from rapid design and prototyping for the manufacturing sector to the entertainment industry [ 3 , 4 , 5 , 6 , 7 ]. Hence, the research focus is shifting towards 3D deep generative models, as rich and flexible 3D representations are rapidly emerging.…”

Section: Introductionmentioning

confidence: 99%

“…Real-time computation allows the random generation of items or characters during the play. Tweaking the design of a 3D-printable object [ 7 ] may also require multiple iterations of a generative model and would also benefit from quick inference. Any application in extended reality, such as generating human models from motion capture data [ 4 ], requires the model to run at the same frequency as the frames.…”

Section: Introductionmentioning

confidence: 99%

PCGen: A Fully Parallelizable Point Cloud Generative Model

Vercheval,

Royen,

Munteanu

et al. 2024

Sensors

View full text Add to dashboard Cite

Generative models have the potential to revolutionize 3D extended reality. A primary obstacle is that augmented and virtual reality need real-time computing. Current state-of-the-art point cloud random generation methods are not fast enough for these applications. We introduce a vector-quantized variational autoencoder model (VQVAE) that can synthesize high-quality point clouds in milliseconds. Unlike previous work in VQVAEs, our model offers a compact sample representation suitable for conditional generation and data exploration with potential applications in rapid prototyping. We achieve this result by combining architectural improvements with an innovative approach for probabilistic random generation. First, we rethink current parallel point cloud autoencoder structures, and we propose several solutions to improve robustness, efficiency and reconstruction quality. Notable contributions in the decoder architecture include an innovative computation layer to process the shape semantic information, an attention mechanism that helps the model focus on different areas and a filter to cover possible sampling errors. Secondly, we introduce a parallel sampling strategy for VQVAE models consisting of a double encoding system, where a variational autoencoder learns how to generate the complex discrete distribution of the VQVAE, not only allowing quick inference but also describing the shape with a few global variables. We compare the proposed decoder and our VQVAE model with established and concurrent work, and we prove, one by one, the validity of the single contributions.

show abstract

X-Hair: 3D Printing Hair-like Structures with Multi-form, Multi-property and Multi-function

Wang,

Ji,

et al. 2024

Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology

View full text Add to dashboard Cite

Style2Fab: Functionality-Aware Segmentation for Fabricating Personalized 3D Models with Generative AI

Cited by 6 publications

References 52 publications

The Evolution of Robin Sequence Treatment Based on the Biomimetic Interdisciplinary Approach: A Historical Review

The Evolution of Robin Sequence Treatment Based on the Biomimetic Interdisciplinary Approach: A Historical Review

PCGen: A Fully Parallelizable Point Cloud Generative Model

X-Hair: 3D Printing Hair-like Structures with Multi-form, Multi-property and Multi-function

Contact Info

Product

Resources

About