Cross-modal Learning for Image-Guided Point Cloud Shape CompletionDownload PDF

Published: 31 Oct 2022, Last Modified: 12 Mar 2024NeurIPS 2022 AcceptReaders: Everyone
Keywords: Point Cloud Completion, View-guided completion, Self-supervised completion, Multimodal Learning
TL;DR: We developed a framework for image-guided point cloud completion under supervised and self-supervised settings.
Abstract: In this paper we explore the recent topic of point cloud completion, guided by an auxiliary image. We show how it is possible to effectively combine the information from the two modalities in a localized latent space, thus avoiding the need for complex point cloud reconstruction methods from single views used by the state-of-the-art. We also investigate a novel self-supervised setting where the auxiliary image provides a supervisory signal to the training process by using a differentiable renderer on the completed point cloud to measure fidelity in the image space. Experiments show significant improvements over state-of-the-art supervised methods for both unimodal and multimodal completion. We also show the effectiveness of the self-supervised approach which outperforms a number of supervised methods and is competitive with the latest supervised models only exploiting point cloud information.
Supplementary Material: pdf
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:2209.09552/code)
12 Replies

Loading