Rethinking Data Input for Point Cloud Upsampling

TL;DR

This paper investigates the differences between patch-based and full-input methods for point cloud upsampling, proposing an average segment input approach and analyzing factors affecting performance.

Contribution

It introduces a novel average segment input method and provides an in-depth analysis of how input types influence upsampling effectiveness.

Findings

Patch-based inputs outperform full model inputs in experiments.

Factors like feature extraction and network architecture significantly impact results.

The study offers insights into designing better point cloud upsampling models.

Abstract

Point cloud upsampling is crucial for tasks like 3D reconstruction. While existing methods rely on patch-based inputs, and there is no research discussing the differences and principles between point cloud model full input and patch based input. Ergo, we propose a novel approach using whole model inputs i.e. Average Segment input. Our experiments on PU1K and ABC datasets reveal that patch-based inputs consistently outperform whole model inputs. To understand this, we will delve into factors in feature extraction, and network architecture that influence upsampling results.