Learning Generative Models of Shape Handles
Learning Generative Models of Shape Handles
复制标题
DOI：
10.1109/cvpr42600.2020.00048
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Matheus Gadelha;Giorgio Gori;Duygu Ceylan;R. Mech;N. Carr;T. Boubekeur;Rui Wang;Subhransu Maji
中科院分区：
文献类型：
--
作者：
Matheus Gadelha;Giorgio Gori;Duygu Ceylan;R. Mech;N. Carr;T. Boubekeur;Rui Wang;Subhransu Maji
我们提出了一种生成模型，用于将3D形状合成为句柄集--接近原始3D形状的轻量级代理--用于交互式编辑、形状解析和构建紧凑的3D表示。我们的模型可以生成具有不同基数和不同类型句柄的句柄集。我们方法的关键是预测形状手柄的参数和存在的深层体系结构，以及能够轻松适应不同类型手柄的新的相似性度量，例如长方体或球面网格。我们利用语义3D标注方面的最新进展以及自动形状摘要技术来监督我们的方法。我们表明，所产生的形状表示不仅是直观的，而且达到了比以前最先进的质量更高的质量。最后，我们演示了我们的方法如何用于交互式形状编辑和完成等应用程序，利用我们的模型学习的潜在空间来指导这些任务。
We present a generative model to synthesize 3D shapes as sets of handles -- lightweight proxies that approximate the original 3D shape -- for applications in interactive editing, shape parsing, and building compact 3D representations. Our model can generate handle sets with varying cardinality and different types of handles. Key to our approach is a deep architecture that predicts both the parameters and existence of shape handles and a novel similarity measure that can easily accommodate different types of handles, such as cuboids or sphere-meshes. We leverage the recent advances in semantic 3D annotation as well as automatic shape summarization techniques to supervise our approach. We show that the resulting shape representations are not only intuitive, but achieve superior quality than previous state-of-the-art. Finally, we demonstrate how our method can be used in applications such as interactive shape editing and completion, leveraging the latent space learned by our model to guide these tasks.