用多平面重建加速3D生成，速度提升1000倍且保持高质量。
DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model
- 用前馈多平面模型替代耗时的几何优化步骤。
- 纹理优化无需训练，4倍快于原有方法且保持一致性。
- 适合快速生成高细节3D内容的创作者与开发者使用。
我们提出 DreamCraft3D++，作为 DreamCraft3D 的扩展版本，实现高效高质量复杂3D资产生成。DreamCraft3D++ 保留原方法的多阶段生成流程，但将耗时的几何雕刻优化替换为前馈式多平面重建模型，使生成速度提升1000倍。在纹理优化方面，提出无需训练的IP-Adapter模块，基于增强的多视角图像进行条件化处理，显著提升纹理与几何的一致性，相较原版DreamBooth微调快4倍。在多样数据集上的实验表明，DreamCraft3D++ 能生成具有复杂几何结构和真实360°纹理的创意3D资产，在质量与速度上均优于现有主流图像到3D方法。完整代码将开源，推动3D内容创作新可能。
原文摘要 · Abstract (English)
We introduce DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets. DreamCraft3D++ inherits the multi-stage generation process of DreamCraft3D, but replaces the time-consuming geometry sculpting optimization with a feed-forward multi-plane based reconstruction model, speeding up the process by 1000x. For texture refinement, we propose a training-free IP-Adapter module that is conditioned on the enhanced multi-view images to enhance texture and geometry consistency, providing a 4x faster alternative to DreamCraft3D's DreamBooth fine-tuning. Experiments on diverse datasets demonstrate DreamCraft3D++'s ability to generate creative 3D assets with intricate geometry and realistic 360° textures, outperforming state-of-the-art image-to-3D methods in quality and speed. The full implementation will be open-sourced to enable new possibilities in 3D content creation.
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。