StraightPCF: Straight Point Cloud Filtering

TL;DR

StraightPCF is a novel deep learning method for point cloud filtering that moves noisy points along straight paths, reducing errors and converging faster to clean surfaces without regularization.

Contribution

It introduces a lightweight network with straight filtering trajectories using VelocityModule and DistanceModule, achieving state-of-the-art results in point cloud filtering.

Findings

Achieves state-of-the-art filtering performance on synthetic and real data.

Uses only 530K parameters, significantly fewer than previous methods.

Produces well-distributed filtered points without regularization.

Abstract

Point cloud filtering is a fundamental 3D vision task, which aims to remove noise while recovering the underlying clean surfaces. State-of-the-art methods remove noise by moving noisy points along stochastic trajectories to the clean surfaces. These methods often require regularization within the training objective and/or during post-processing, to ensure fidelity. In this paper, we introduce StraightPCF, a new deep learning based method for point cloud filtering. It works by moving noisy points along straight paths, thus reducing discretization errors while ensuring faster convergence to the clean surfaces. We model noisy patches as intermediate states between high noise patch variants and their clean counterparts, and design the VelocityModule to infer a constant flow velocity from the former to the latter. This constant flow leads to straight filtering trajectories. In addition, we introduce a DistanceModule that scales the straight trajectory using an estimated distance scalar to attain convergence near the clean surface. Our network is lightweight and only has $\sim530K$ parameters, being 17% of IterativePFN (a most recent point cloud filtering network). Extensive experiments on both synthetic and real-world data show our method achieves state-of-the-art results. Our method also demonstrates nice distributions of filtered points without the need for regularization. The implementation code can be found at: https://github.com/ddsediri/StraightPCF.