CRAFT: Designing Creative and Functional 3D Objects

TL;DR

This paper introduces CRAFT, a method for synthesizing body-aware 3D objects from base meshes guided by text or images, enabling realistic virtual and physical object creation with minimal manual effort.

Contribution

The paper presents a novel mesh deformation approach that optimizes for semantic alignment and contact constraints, allowing automatic creation of functional 3D objects from diverse inputs.

Findings

Effective synthesis of body-aware 3D objects demonstrated

Method achieves high semantic and contact accuracy

Enables virtual simulation and real-world fabrication

Abstract

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.