PU-EVA: An Edge Vector based Approximation Solution for Flexible-scale Point Cloud Upsampling

TL;DR

PU-EVA introduces a novel edge vector based approximation method that enables flexible-scale point cloud upsampling, outperforming existing techniques in quality and adaptability.

Contribution

The paper proposes a new edge vector based affine combination approach for flexible-scale point cloud upsampling, decoupling scale from network architecture.

Findings

Outperforms state-of-the-art in proximity-to-surface accuracy

Achieves more uniform point distribution

Preserves geometric details effectively

Abstract

High-quality point clouds have practical significance for point-based rendering, semantic understanding, and surface reconstruction. Upsampling sparse, noisy and nonuniform point clouds for a denser and more regular approximation of target objects is a desirable but challenging task. Most existing methods duplicate point features for upsampling, constraining the upsampling scales at a fixed rate. In this work, the flexible upsampling rates are achieved via edge vector based affine combinations, and a novel design of Edge Vector based Approximation for Flexible-scale Point clouds Upsampling (PU-EVA) is proposed. The edge vector based approximation encodes the neighboring connectivity via affine combinations based on edge vectors, and restricts the approximation error within the second-order term of Taylor's Expansion. The EVA upsampling decouples the upsampling scales with network architecture, achieving the flexible upsampling rates in one-time training. Qualitative and quantitative evaluations demonstrate that the proposed PU-EVA outperforms the state-of-the-art in terms of proximity-to-surface, distribution uniformity, and geometric details preservation.