Rethinking Point Cloud Filtering: A Non-Local Position Based Approach

TL;DR

This paper introduces a novel non-local, position-based point cloud filtering method that preserves sharp features without relying on normal information, outperforming existing position and normal based techniques.

Contribution

Proposes a non-learning, non-normal, non-local point cloud filtering approach that effectively preserves features by aggregating similar patches in a canonical space.

Findings

Outperforms existing position-based filtering methods.

Generates results comparable or superior to normal-based techniques.

Validated through extensive experiments.

Abstract

Existing position based point cloud filtering methods can hardly preserve sharp geometric features. In this paper, we rethink point cloud filtering from a non-learning non-local non-normal perspective, and propose a novel position based approach for feature-preserving point cloud filtering. Unlike normal based techniques, our method does not require the normal information. The core idea is to first design a similarity metric to search the non-local similar patches of a queried local patch. We then map the non-local similar patches into a canonical space and aggregate the non-local information. The aggregated outcome (i.e. coordinate) will be inversely mapped into the original space. Our method is simple yet effective. Extensive experiments validate our method, and show that it generally outperforms position based methods (deep learning and non-learning), and generates better or comparable outcomes to normal based techniques (deep learning and non-learning).