Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion

TL;DR

EGIInet is a new framework for cross-modal point cloud completion that effectively combines 2D images and 3D data through modal alignment and explicit guidance, achieving state-of-the-art results.

Contribution

The paper introduces a unified encoding process and an explicit information interaction strategy for improved modal alignment in point cloud completion.

Findings

Achieved +16% Chamfer Distance improvement over XMFnet.

Outperformed previous methods with fewer parameters.

Validated effectiveness through extensive experiments.

Abstract

In this paper, we explore a novel framework, EGIInet (Explicitly Guided Information Interaction Network), a model for View-guided Point cloud Completion (ViPC) task, which aims to restore a complete point cloud from a partial one with a single view image. In comparison with previous methods that relied on the global semantics of input images, EGIInet efficiently combines the information from two modalities by leveraging the geometric nature of the completion task. Specifically, we propose an explicitly guided information interaction strategy supported by modal alignment for point cloud completion. First, in contrast to previous methods which simply use 2D and 3D backbones to encode features respectively, we unified the encoding process to promote modal alignment. Second, we propose a novel explicitly guided information interaction strategy that could help the network identify critical information within images, thus achieving better guidance for completion. Extensive experiments demonstrate the effectiveness of our framework, and we achieved a new state-of-the-art (+16% CD over XMFnet) in benchmark datasets despite using fewer parameters than the previous methods. The pre-trained model and code and are available at https://github.com/WHU-USI3DV/EGIInet.