让3D生成模型自动生成少用支撑的可打印结构。
From Prompts to Printable Models: Support-Effective 3D Generation via Offset Direct Preference Optimization
- 用偏移直接偏好优化，训练时加入支撑模拟
- 在两个数据集上支撑体积减少超40%，打印性显著提升
- 适合关注3D打印可持续性和生产效率的研究者
当前文本到3D生成模型注重视觉保真度，但常忽略物理可打印性，导致生成几何体需大量支撑结构。本文提出SEG（支持有效生成）框架，将偏移直接偏好优化（ODPO）融入3D生成流程，直接优化模型以最小化支撑材料使用。通过在训练中引入支撑结构模拟，SEG促使生成具有内在低支撑需求的几何形状，从而减少材料浪费和生产时间。我们在Thingi10k-Val和GPT-3DP-Val两个基准数据集上进行了广泛实验，结果表明，SEG在支撑体积减少和可打印性方面显著优于TRELLIS、DPO和DRO等基线模型。定性结果还显示，SEG在保持对输入提示高保真度的同时，大幅降低了对支撑结构的需求。研究结果表明，通过在生成过程中直接优化模型，SEG有潜力推动3D打印向更可持续、高效的数字制造范式转变。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。