DeepAI AI Chat
Log In Sign Up

PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery

by   Weibing Zhao, et al.

Point Cloud Sampling and Recovery (PCSR) is critical for massive real-time point cloud collection and processing since raw data usually requires large storage and computation. In this paper, we address a fundamental problem in PCSR: How to downsample the dense point cloud with arbitrary scales while preserving the local topology of discarding points in a case-agnostic manner (i.e. without additional storage for point relationship)? We propose a novel Locally Invertible Embedding for point cloud adaptive sampling and recovery (PointLIE). Instead of learning to predict the underlying geometry details in a seemingly plausible manner, PointLIE unifies point cloud sampling and upsampling to one single framework through bi-directional learning. Specifically, PointLIE recursively samples and adjusts neighboring points on each scale. Then it encodes the neighboring offsets of sampled points to a latent space and thus decouples the sampled points and the corresponding local geometric relationship. Once the latent space is determined and that the deep model is optimized, the recovery process could be conducted by passing the recover-pleasing sampled points and a randomly-drawn embedding to the same network through an invertible operation. Such a scheme could guarantee the fidelity of dense point recovery from sampled points. Extensive experiments demonstrate that the proposed PointLIE outperforms state-of-the-arts both quantitatively and qualitatively. Our code is released through


page 6

page 11

page 12

page 13


PointNorm: Normalization is All You Need for Point Cloud Analysis

Point cloud analysis is challenging due to the irregularity of the point...

APSNet: Attention Based Point Cloud Sampling

Processing large point clouds is a challenging task. Therefore, the data...

Density-preserving Deep Point Cloud Compression

Local density of point clouds is crucial for representing local details,...

Neural Points: Point Cloud Representation with Neural Fields

In this paper, we propose Neural Points, a novel point cloud representat...

SampleNet: Differentiable Point Cloud Sampling

There is a growing number of tasks that work directly on point clouds. A...

Towards Stratified Space Learning: Linearly Embedded Graphs

In this paper, we consider the simplest class of stratified spaces – lin...

Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloud

Point cloud upsampling is vital for the quality of the mesh in three-dim...

Code Repositories


PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery (IJCAI 2021)

view repo