Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion
Ruikai Cui (Australian National University), Shi Qiu (ANU), Saeed Anwar (The Australian National University), Jing Zhang (Australian National University), Nick Barnes (ANU)*
The 33rd British Machine Vision Conference
Abstract
Unsupervised point cloud completion aims to infer the whole geometry of a partial object observation without requiring partial-complete correspondence. Differ 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 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.Video
Citation
@inproceedings{Cui_2022_BMVC,
author = {Ruikai Cui and Shi Qiu and Saeed Anwar and Jing Zhang and Nick Barnes},
title = {Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0048.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by