arXiv:2511.09298v2 Announce Type: replace 
Abstract: The rise of 3D generative models has enabled automatic 3D geometry and texture synthesis from multimodal inputs (e.g., text or images). However, these methods often ignore physical constraints and manufacturability considerations. In this work, we address the challenge of producing 3D designs that are both lightweight and self-supporting. We present DensiCrafter, a framework for generating lightweight, self-supporting 3D hollow structures by optimizing the density field. Starting from coarse voxel grids produced by Trellis, we interpret these as continuous density fields to optimize and introduce three differentiable, physically constrained, and simulation-free loss terms. Additionally, a mass regularization penalizes unnecessary material, while a restricted optimization domain preserves the outer surface. Our method seamlessly integrates with pretrained Trellis-based models (e.g., Trellis, DSO) without any architectural changes. In extensive evaluations, we achieve up to 43% reduction in material mass on the text-to-3D task. Compared to state-of-the-art baselines, our method could improve the stability and maintain high geometric fidelity. Real-world 3D-printing experiments confirm that our hollow designs can be reliably fabricated and could be self-supporting.

تم تقديم DensiCrafter كإطار لتوليد هياكل مجوفة خفيفة الوزن وقابلة للدعم الذاتي من خلال تحسين مجالات الكثافة، مما يعالج قيود نماذج الجيل الثلاثي الأبعاد الحالية التي غالبًا ما تتجاهل القيود الفيزيائية وقابلية التصنيع. تستخدم هذه الطريقة شبكات فوكسل خشنة من Trellis وتدمج مصطلحات خسارة قابلة للاشتقاق لتحسين كفاءة التصميم.

Se ha presentado DensiCrafter como un marco para generar estructuras huecas ligeras y autoportantes mediante la optimización de campos de densidad, abordando las limitaciones de los modelos generativos 3D existentes que a menudo pasan por alto las restricciones físicas y la fabricabilidad. Este método utiliza cuadrículas voxel gruesas de Trellis e incorpora términos de pérdida diferenciables para mejorar la eficiencia del diseño.

DensiCrafter a été présenté comme un cadre pour générer des structures creuses légères et autoportantes en optimisant les champs de densité, répondant aux limites des modèles génératifs 3D existants qui négligent souvent les contraintes physiques et la fabricabilité. Cette méthode utilise des grilles voxel grossières de Trellis et intègre des termes de perte différentiables pour améliorer l'efficacité de la conception.

DensiCrafter has been introduced as a framework for generating lightweight, self-supporting 3D hollow structures by optimizing density fields, addressing the limitations of existing 3D generative models that often overlook physical constraints and manufacturability. This method utilizes coarse voxel grids from Trellis and incorporates differentiable loss terms to enhance design efficiency.

DensiCrafter: Physically-Constrained Generation and Fabrication of Self-Supporting Hollow Structures

Was this article worth reading? Share it

PlantFCE Model Builder

File Architect

Z3D

VECTARY

Artefacts.ai

CreativeFabrica

Ready to build your own newsroom?