From Prompts to Printable Models: Support-Effective 3D Generation via Offset Direct Preference Optimization

TL;DR

This paper presents SEG, a novel 3D model generation framework that optimizes for minimal support structures during creation, reducing material waste and improving printability without sacrificing fidelity.

Contribution

SEG introduces Offset Direct Preference Optimization into 3D generation, enabling support-effective models that inherently require less support material.

Findings

SEG outperforms baseline models in support volume reduction

SEG maintains high fidelity to input prompts

Supports more sustainable and efficient 3D printing

Abstract

Current text-to-3D models prioritize visual fidelity but often neglect physical fabricability, resulting in geometries requiring excessive support structures. This paper introduces SEG (\textit{\underline{S}upport-\underline{E}ffective \underline{G}eneration}), a novel framework that integrates Direct Preference Optimization with an Offset (ODPO) into the 3D generation pipeline to directly optimize models for minimal support material usage. By incorporating support structure simulation into the training process, SEG encourages the generation of geometries that inherently require fewer supports, thus reducing material waste and production time. We demonstrate SEG's effectiveness through extensive experiments on two benchmark datasets, Thingi10k-Val and GPT-3DP-Val, showing that SEG significantly outperforms baseline models such as TRELLIS, DPO, and DRO in terms of support volume reduction and printability. Qualitative results further reveal that SEG maintains high fidelity to input prompts while minimizing the need for support structures. Our findings highlight the potential of SEG to transform 3D printing by directly optimizing models during the generative process, paving the way for more sustainable and efficient digital fabrication practices.