3D Shape Completion with Multi-view Consistent Inference

TL;DR

This paper introduces a multi-view consistent inference method for 3D shape completion that enforces geometric consistency among views, leading to more accurate shape reconstructions from partial observations.

Contribution

It proposes a novel energy minimization framework with a regularization term for geometric consistency, improving upon view-based shape completion methods.

Findings

Achieves more accurate shape completion results than previous methods.

Enforces geometric consistency among multiple views during inference.

Demonstrates improved performance on standard benchmarks.

Abstract

3D shape completion is important to enable machines to perceive the complete geometry of objects from partial observations. To address this problem, view-based methods have been presented. These methods represent shapes as multiple depth images, which can be back-projected to yield corresponding 3D point clouds, and they perform shape completion by learning to complete each depth image using neural networks. While view-based methods lead to state-of-the-art results, they currently do not enforce geometric consistency among the completed views during the inference stage. To resolve this issue, we propose a multi-view consistent inference technique for 3D shape completion, which we express as an energy minimization problem including a data term and a regularization term. We formulate the regularization term as a consistency loss that encourages geometric consistency among multiple views, while the data term guarantees that the optimized views do not drift away too much from a learned shape descriptor. Experimental results demonstrate that our method completes shapes more accurately than previous techniques.