Exploring Cross-Point Embeddings for 3D Dense Uncertainty Estimation

by   Kaiwen Cai, et al.

Dense prediction tasks are common for 3D point clouds, but the inherent uncertainties in massive points and their embeddings have long been ignored. In this work, we present CUE, a novel uncertainty estimation method for dense prediction tasks of 3D point clouds. Inspired by metric learning, the key idea of CUE is to explore cross-point embeddings upon a conventional dense prediction pipeline. Specifically, CUE involves building a probabilistic embedding model and then enforcing metric alignments of massive points in the embedding space. We demonstrate that CUE is a generic and effective tool for dense uncertainty estimation of 3D point clouds in two different tasks: (1) in 3D geometric feature learning we for the first time obtain well-calibrated dense uncertainty, and (2) in semantic segmentation we reduce uncertainty`s Expected Calibration Error of the state-of-the-arts by 43.8 are estimated without compromising predictive performance.


page 1

page 5

page 7


Point2Skeleton: Learning Skeletal Representations from Point Clouds

We introduce Point2Skeleton, an unsupervised method to learn skeletal re...

PointWise:An Unsupervised Point-wise Feature Learning Network

The availability and plethora of unlabeled point-clouds as well as their...

Augmented Semantic Signatures of Airborne LiDAR Point Clouds for Comparison

LiDAR point clouds provide rich geometric information, which is particul...

Attention Models for Point Clouds in Deep Learning: A Survey

Recently, the advancement of 3D point clouds in deep learning has attrac...

Rethinking Task and Metrics of Instance Segmentation on 3D Point Clouds

Instance segmentation on 3D point clouds is one of the most extensively ...

Learning Implicit Functions for Dense 3D Shape Correspondence of Generic Objects

The objective of this paper is to learn dense 3D shape correspondence fo...

A Convolutional Architecture for 3D Model Embedding

During the last years, many advances have been made in tasks like3D mode...

Please sign up or login with your details

Forgot password? Click here to reset