SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network

TL;DR

This paper introduces SPU-IMR, a self-supervised method that treats point cloud upsampling as a global shape completion task, using iterative patch recovery to generate dense, uniform point clouds from sparse inputs.

Contribution

It proposes a novel self-supervised approach that divides point clouds into patches, masks some, and iteratively completes missing parts, differing from traditional interpolation methods.

Findings

Outperforms existing self-supervised methods in experiments

Achieves superior qualitative and quantitative results

Effectively restores complete point clouds from sparse inputs

Abstract

Point cloud upsampling aims to generate dense and uniformly distributed point sets from sparse point clouds. Existing point cloud upsampling methods typically approach the task as an interpolation problem. They achieve upsampling by performing local interpolation between point clouds or in the feature space, then regressing the interpolated points to appropriate positions. By contrast, our proposed method treats point cloud upsampling as a global shape completion problem. Specifically, our method first divides the point cloud into multiple patches. Then, a masking operation is applied to remove some patches, leaving visible point cloud patches. Finally, our custom-designed neural network iterative completes the missing sections of the point cloud through the visible parts. During testing, by selecting different mask sequences, we can restore various complete patches. A sufficiently dense upsampled point cloud can be obtained by merging all the completed patches. We demonstrate the superior performance of our method through both quantitative and qualitative experiments, showing overall superiority against both existing self-supervised and supervised methods.