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.
翻译:我们建议从局部观测点云中完成 3D 形状的新方法。 现有的方法要么以全球潜伏代码操作,该代码限制其模型的表达性, 要么自动递增地估计当地特征, 这种方法在计算上非常广泛。 相反, 我们的方法通过一个单一的进化前网络, 将整个本地特征字段估算成一个问题, 将这一问题描述为该对象特征量的“ 微量完成问题 ” 。 由于本地特性量的冗余, 这个 微量完成问题可以进一步降低到估计特征量的能因因素。 一个带有微小 MLPs 的等级变异自动电解码( VAE ) 用于概率性地估计整个功能量的能量因素。 拟议的方法的有效性通过定量和定性将其与状态方法进行比较而得到验证。 进一步的通货膨胀研究还表明, 有必要采用一个分级结构来捕捉到可能形状的多式分布。