当前位置: X-MOL 学术arXiv.cs.GR › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Learning Mesh Representations via Binary Space Partitioning Tree Networks
arXiv - CS - Graphics Pub Date : 2021-06-27 , DOI: arxiv-2106.14274
Zhiqin Chen, Andrea Tagliasacchi, Hao Zhang

Polygonal meshes are ubiquitous, but have only played a relatively minor role in the deep learning revolution. State-of-the-art neural generative models for 3D shapes learn implicit functions and generate meshes via expensive iso-surfacing. We overcome these challenges by employing a classical spatial data structure from computer graphics, Binary Space Partitioning (BSP), to facilitate 3D learning. The core operation of BSP involves recursive subdivision of 3D space to obtain convex sets. By exploiting this property, we devise BSP-Net, a network that learns to represent a 3D shape via convex decomposition without supervision. The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built over a set of planes, where the planes and convexes are both defined by learned network weights. BSP-Net directly outputs polygonal meshes from the inferred convexes. The generated meshes are watertight, compact (i.e., low-poly), and well suited to represent sharp geometry. We show that the reconstruction quality by BSP-Net is competitive with those from state-of-the-art methods while using much fewer primitives. We also explore variations to BSP-Net including using a more generic decoder for reconstruction, more general primitives than planes, as well as training a generative model with variational auto-encoders. Code is available at https://github.com/czq142857/BSP-NET-original.

中文翻译:

通过二元空间划分树网络学习网格表示

多边形网格无处不在,但在深度学习革命中只发挥了相对较小的作用。最先进的 3D 形状神经生成模型学习隐式函数并通过昂贵的等值曲面生成网格。我们通过采用计算机图形学中的经典空间数据结构二进制空间分区 (BSP) 来促进 3D 学习,从而克服了这些挑战。BSP 的核心操作涉及递归细分 3D 空间以获得凸集。通过利用这一特性,我们设计了 BSP-Net,这是一种在没有监督的情况下通过凸分解学习表示 3D 形状的网络。该网络被训练使用从在一组平面上构建的 BSP 树获得的一组凸面来重建形状,其中平面和凸面都由学习到的网络权重定义。BSP-Net 直接从推断的凸面输出多边形网格。生成的网格是防水的、紧凑的(即低多边形),非常适合表示锐利的几何图形。我们表明,BSP-Net 的重建质量与最先进方法的重建质量具有竞争力,同时使用的原语要少得多。我们还探索了 BSP-Net 的变体,包括使用更通用的解码器进行重建、比平面更通用的基元,以及使用变分自动编码器训练生成模型。代码可在 https://github.com/czq142857/BSP-NET-original 获得。我们表明,BSP-Net 的重建质量与最先进方法的重建质量具有竞争力,同时使用的原语要少得多。我们还探索了 BSP-Net 的变体,包括使用更通用的解码器进行重建、比平面更通用的基元,以及使用变分自动编码器训练生成模型。代码可在 https://github.com/czq142857/BSP-NET-original 获得。我们表明,BSP-Net 的重建质量与最先进方法的重建质量具有竞争力,同时使用的原语要少得多。我们还探索了 BSP-Net 的变体,包括使用更通用的解码器进行重建、比平面更通用的基元,以及使用变分自动编码器训练生成模型。代码可在 https://github.com/czq142857/BSP-NET-original 获得。
更新日期:2021-06-29
down
wechat
bug