PU-MFA : Point Cloud Up-sampling via Multi-scale Features Attention

TL;DR

This paper introduces PU-MFA, a novel deep learning method that combines multi-scale features and attention mechanisms within a U-Net structure to improve point cloud up-sampling, achieving superior results on synthetic and real datasets.

Contribution

PU-MFA is the first to integrate multi-scale features and attention mechanisms for point cloud up-sampling within a U-Net framework, enhancing global feature refinement.

Findings

PU-MFA outperforms existing methods in quantitative metrics.

PU-MFA produces higher quality and more detailed up-sampled point clouds.

Visualization confirms effective use of multi-scale features.

Abstract

Recently, research using point clouds has been increasing with the development of 3D scanner technology. According to this trend, the demand for high-quality point clouds is increasing, but there is still a problem with the high cost of obtaining high-quality point clouds. Therefore, with the recent remarkable development of deep learning, point cloud up-sampling research, which uses deep learning to generate high-quality point clouds from low-quality point clouds, is one of the fields attracting considerable attention. This paper proposes a new point cloud up-sampling method called Point cloud Up-sampling via Multi-scale Features Attention (PU-MFA). Inspired by previous studies that reported good performance using the multi-scale features or attention mechanisms, PU-MFA merges the two through a U-Net structure. In addition, PU-MFA adaptively uses multi-scale features to refine the global features effectively. The performance of PU-MFA was compared with other state-of-the-art methods through various experiments using the PU-GAN dataset, which is a synthetic point cloud dataset, and the KITTI dataset, which is the real-scanned point cloud dataset. In various experimental results, PU-MFA showed superior performance in quantitative and qualitative evaluation compared to other state-of-the-art methods, proving the effectiveness of the proposed method. The attention map of PU-MFA was also visualized to show the effect of multi-scale features.