Hyperbolic-constraint Point Cloud Reconstruction from Single RGB-D Images

TL;DR

This paper introduces a novel hyperbolic space approach for single-view 3D point cloud reconstruction from RGB-D images, improving hierarchical structure understanding and reconstruction accuracy.

Contribution

It proposes a hyperbolic space framework with a hyperbolic Chamfer distance and adaptive boundary conditions, advancing 3D reconstruction methods.

Findings

Outperforms existing models in 3D reconstruction tasks

Enhances feature extraction capabilities

Demonstrates the effectiveness of hyperbolic space in modeling complex structures

Abstract

Reconstructing desired objects and scenes has long been a primary goal in 3D computer vision. Single-view point cloud reconstruction has become a popular technique due to its low cost and accurate results. However, single-view reconstruction methods often rely on expensive CAD models and complex geometric priors. Effectively utilizing prior knowledge about the data remains a challenge. In this paper, we introduce hyperbolic space to 3D point cloud reconstruction, enabling the model to represent and understand complex hierarchical structures in point clouds with low distortion. We build upon previous methods by proposing a hyperbolic Chamfer distance and a regularized triplet loss to enhance the relationship between partial and complete point clouds. Additionally, we design adaptive boundary conditions to improve the model's understanding and reconstruction of 3D structures. Our model outperforms most existing models, and ablation studies demonstrate the significance of our model and its components. Experimental results show that our method significantly improves feature extraction capabilities. Our model achieves outstanding performance in 3D reconstruction tasks.