Probabilistic Shape Completion by Estimating Canonical Factors with Hierarchical VAE

TL;DR

This paper introduces a hierarchical VAE-based method for 3D shape completion from partial point clouds, efficiently estimating local features via tensor completion and canonical factors, outperforming existing approaches.

Contribution

The novel approach models local feature volumes as tensor completion problems and estimates canonical factors with a hierarchical VAE, improving expressiveness and efficiency.

Findings

Outperforms state-of-the-art methods quantitatively and qualitatively.

Hierarchical architecture captures multimodal shape distributions effectively.

Ablation studies confirm the importance of hierarchical design.

Abstract

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.