Joint Point Cloud Upsampling and Cleaning with Octree-based CNNs

TL;DR

This paper introduces a simple, efficient octree-based 3D U-Net approach for joint point cloud upsampling and cleaning, achieving state-of-the-art results with significantly faster inference.

Contribution

It presents a novel, streamlined method that processes entire point clouds directly, reducing complexity and inference time compared to previous patch-based approaches.

Findings

Achieves at least 47 times faster inference

Attains state-of-the-art performance on benchmarks

Simplifies implementation of point cloud processing

Abstract

Recovering dense and uniformly distributed point clouds from sparse or noisy data remains a significant challenge. Recently, great progress has been made on these tasks, but usually at the cost of increasingly intricate modules or complicated network architectures, leading to long inference time and huge resource consumption. Instead, we embrace simplicity and present a simple yet efficient method for jointly upsampling and cleaning point clouds. Our method leverages an off-the-shelf octree-based 3D U-Net (OUNet) with minor modifications, enabling the upsampling and cleaning tasks within a single network. Our network directly processes each input point cloud as a whole instead of processing each point cloud patch as in previous works, which significantly eases the implementation and brings at least 47 times faster inference. Extensive experiments demonstrate that our method achieves state-of-the-art performances under huge efficiency advantages on a series of benchmarks. We expect our method to serve simple baselines and inspire researchers to rethink the method design on point cloud upsampling and cleaning.