Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion
This addresses the problem of inferring complete 3D object geometries from partial observations without correspondence data, representing a novel generative approach rather than an incremental improvement.
The paper tackles unsupervised point cloud completion by proposing a generative framework that transforms partial shape encodings into complete ones using a latent transport module based on an energy-based model, achieving high-fidelity results that outperform state-of-the-art models by a significant margin.
Unsupervised point cloud completion aims to infer the whole geometry of a partial object observation without requiring partial-complete correspondence. Differing from existing deterministic approaches, we advocate generative modeling based unsupervised point cloud completion to explore the missing correspondence. Specifically, we propose a novel framework that performs completion by transforming a partial shape encoding into a complete one using a latent transport module, and it is designed as a latent-space energy-based model (EBM) in an encoder-decoder architecture, aiming to learn a probability distribution conditioned on the partial shape encoding. To train the latent code transport module and the encoder-decoder network jointly, we introduce a residual sampling strategy, where the residual captures the domain gap between partial and complete shape latent spaces. As a generative model-based framework, our method can produce uncertainty maps consistent with human perception, leading to explainable unsupervised point cloud completion. We experimentally show that the proposed method produces high-fidelity completion results, outperforming state-of-the-art models by a significant margin.