arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.08310cs.CVcs.AI
收藏

使用合成训练的生成模型对文化文物进行一对多3D几何重建

One-to-many Reconstruction of 3D Geometry of cultural Artifacts using a synthetically trained Generative Model

Fraunhofer Institute for Computer Graphics Research IGD(弗劳恩霍夫计算机图形学研究所);Interactive Graphics Research Group, TU Darmstadt(达姆施塔特工业大学交互图形学研究组)

Thomas Pöllabauer, Julius Kühn, Jiayi Li, Arjan Kuijper

AI总结:

提出一种基于合成数据训练的生成模型,从单张历史素描生成多种3D几何重建,支持多模态输入引导,适用于小样本场景并允许专家交互重建丢失文物外观。

摘要:

使用单张图像估计物体的3D形状是一个难题。现代方法基于真实照片对一般物体取得了良好效果,但在历史素描等表现力较弱的表示上效果较差。我们的自动化方法从描绘中世纪雕像的单张素描生成多种详细的3D表示,并可通过文本提示等多模态输入进行引导。它仅依赖合成数据进行训练,使其在仅有少量训练样本的情况下也能适用。我们的解决方案允许领域专家(如策展人)交互式地重建丢失文物的潜在外观。

英文摘要:

Estimating the 3D shape of an object using a single image is a difficult problem. Modern approaches achieve good results for general objects, based on real photographs, but worse results on less expressive representations such as historic sketches. Our automated approach generates a variety of detailed 3D representation from a single sketch, depicting a medieval statue, and can be guided by multi-modal inputs, such as text prompts. It relies solely on synthetic data for training, making it adoptable even in cases of only small numbers of training examples. Our solution allows domain experts such as a curators to interactively reconstruct potential appearances of lost artifacts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑