arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.03370cs.CV
收藏

基于分层VAE估计典型因子的概率形状完备化

Probabilistic Shape Completion by Estimating Canonical Factors with Hierarchical VAE

University of Pennsylvania(宾夕法尼亚大学)

Wen Jiang, Kostas Daniilidis

摘要:

我们提出了一种新的方法,从一个点云的部分观察的三维形状完成。现有的方法要么在全局潜在代码上操作,这限制了其模型的表达能力,要么自回归估计局部特征,这是高度计算量大的。相反,我们的方法通过将这个问题公式化为对象特征体积上的张量完成问题,通过单个前馈网络来估计整个局部特征场。由于局部特征体的冗余性,该张量完备化问题可以进一步简化为特征体的正则因子估计。一个层次的变分自编码器(VAE)与微小的MLP被用来概率估计的典范因子的完整的特征量。通过与现有方法的定量和定性比较,验证了该方法的有效性。进一步的消融研究还表明,需要采用分层结构来捕获可能形状的多峰分布。

英文摘要:

We propose a novel method for 3D shape completion from a partial observation of a point cloud. Existing methods either operate on a global latent code, which limits the expressiveness of their model, or autoregressively estimate the local features, which is highly computationally extensive. Instead, our method estimates the entire local feature field by a single feedforward network by formulating this problem as a tensor completion problem on the feature volume of the object. Due to the redundancy of local feature volumes, this tensor completion problem can be further reduced to estimating the canonical factors of the feature volume. A hierarchical variational autoencoder (VAE) with tiny MLPs is used to probabilistically estimate the canonical factors of the complete feature volume. The effectiveness of the proposed method is validated by comparing it with the state-of-the-art method quantitatively and qualitatively. Further ablation studies also show the need to adopt a hierarchical architecture to capture the multimodal distribution of possible shapes.

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。

↑