Salvato in:
Dettagli Bibliografici
Autori principali: Guo, Michelle, Tang, Mia, Cha, Hannah, Zhang, Ruohan, Liu, C. Karen, Wu, Jiajun
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.03889
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913763010019328
author Guo, Michelle
Tang, Mia
Cha, Hannah
Zhang, Ruohan
Liu, C. Karen
Wu, Jiajun
author_facet Guo, Michelle
Tang, Mia
Cha, Hannah
Zhang, Ruohan
Liu, C. Karen
Wu, Jiajun
contents For designing a wide range of everyday objects, the design process should be aware of both the human body and the underlying semantics of the design specification. However, these two objectives present significant challenges to the current AI-based designing tools. In this work, we present a method to synthesize body-aware 3D objects from a base mesh given an input body geometry and either text or image as guidance. The generated objects can be simulated on virtual characters, or fabricated for real-world use. We propose to use a mesh deformation procedure that optimizes for both semantic alignment as well as contact and penetration losses. Using our method, users can generate both virtual or real-world objects from text, image, or sketch, without the need for manual artist intervention. We present both qualitative and quantitative results on various object categories, demonstrating the effectiveness of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03889
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CRAFT: Designing Creative and Functional 3D Objects
Guo, Michelle
Tang, Mia
Cha, Hannah
Zhang, Ruohan
Liu, C. Karen
Wu, Jiajun
Computer Vision and Pattern Recognition
Graphics
For designing a wide range of everyday objects, the design process should be aware of both the human body and the underlying semantics of the design specification. However, these two objectives present significant challenges to the current AI-based designing tools. In this work, we present a method to synthesize body-aware 3D objects from a base mesh given an input body geometry and either text or image as guidance. The generated objects can be simulated on virtual characters, or fabricated for real-world use. We propose to use a mesh deformation procedure that optimizes for both semantic alignment as well as contact and penetration losses. Using our method, users can generate both virtual or real-world objects from text, image, or sketch, without the need for manual artist intervention. We present both qualitative and quantitative results on various object categories, demonstrating the effectiveness of our approach.
title CRAFT: Designing Creative and Functional 3D Objects
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2412.03889