Surface Representation for Point Clouds

by   Haoxi Ran, et al.

Most prior work represents the shapes of point clouds by coordinates. However, it is insufficient to describe the local geometry directly. In this paper, we present RepSurf (representative surfaces), a novel representation of point clouds to explicitly depict the very local structure. We explore two variants of RepSurf, Triangular RepSurf and Umbrella RepSurf inspired by triangle meshes and umbrella curvature in computer graphics. We compute the representations of RepSurf by predefined geometric priors after surface reconstruction. RepSurf can be a plug-and-play module for most point cloud models thanks to its free collaboration with irregular points. Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency. With an increase of around 0.008M number of parameters, 0.04G FLOPs, and 1.12ms inference time, our method achieves 94.7% (+0.5%) on ModelNet40, and 84.6% (+1.8%) on ScanObjectNN for classification, while 74.3% (+0.8%) mIoU on S3DIS 6-fold, and 70.0% (+1.6%) mIoU on ScanNet for segmentation. For detection, previous state-of-the-art detector with our RepSurf obtains 71.2% (+2.1%) mAP_25, 54.8% (+2.0%) mAP_50 on ScanNetV2, and 64.9% (+1.9%) mAP_25, 47.7% (+2.5%) mAP_50 on SUN RGB-D. Our lightweight Triangular RepSurf performs its excellence on these benchmarks as well. The code is publicly available at <>.


page 3

page 13


GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation

The recent neural implicit representation-based methods have greatly adv...

Dynamic Polygon Clouds: Representation and Compression for VR/AR

We introduce the polygon cloud, also known as a polygon set or soup, a...

Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis

Point clouds are characterized by irregularity and unstructuredness, whi...

Recurrent Slice Networks for 3D Segmentation on Point Clouds

In this paper, we present a conceptually simple and powerful framework, ...

WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation

We propose WarpingGAN, an effective and efficient 3D point cloud generat...

Learning to Generate Dense Point Clouds with Textures on Multiple Categories

3D reconstruction from images is a core problem in computer vision. With...

Tensorformer: Normalized Matrix Attention Transformer for High-quality Point Cloud Reconstruction

Surface reconstruction from raw point clouds has been studied for decade...

Please sign up or login with your details

Forgot password? Click here to reset