单图生成可编辑的3D几何细节贴图，让艺术家轻松添加精细模型部件。
GenVDM: Generating Vector Displacement Maps From a Single Image
- 从单张图像生成多视角法线图，再重建向量位移贴图
- 新算法实现3D物体VDM提取，准确率优于现有方法
- 适合3D建模师快速添加可编辑几何细节
我们提出首个生成向量位移贴图（VDM）的方法：一种常用于3D建模的参数化、高精度几何模板。给定单张输入图像，方法首先生成多视角法线图，再通过创新的重建流程恢复出VDM。同时提出高效算法从3D物体中提取VDM，并构建首个学术级VDM数据集。与聚焦完整形状生成的现有3D生成模型不同，本方法专注于生成可无缝贴附于物体表面的几何部件。该方法为艺术家提供丰富控制力，用于向3D模型添加细节。实验表明，本方法优于现有基线。生成VDM还带来额外优势：可通过2D图像编辑定制和优化3D细节。
原文摘要 · Abstract (English)
We introduce the first method for generating Vector Displacement Maps (VDMs): parameterized, detailed geometric stamps commonly used in 3D modeling. Given a single input image, our method first generates multi-view normal maps and then reconstructs a VDM from the normals via a novel reconstruction pipeline. We also propose an efficient algorithm for extracting VDMs from 3D objects, and present the first academic VDM dataset. Compared to existing 3D generative models focusing on complete shapes, we focus on generating parts that can be seamlessly attached to shape surfaces. The method gives artists rich control over adding geometric details to a 3D shape. Experiments demonstrate that our approach outperforms existing baselines. Generating VDMs offers additional benefits, such as using 2D image editing to customize and refine 3D details.
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。