PREDATOR: Registration of 3D Point Clouds with Low Overlap

11/25/2020
by   Shengyu Huang, et al.
0

We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region. Different from previous work, our model is specifically designed to handle (also) point-cloud pairs with low overlap. Its key novelty is an overlap-attention block for early information exchange between the latent encodings of the two point clouds. In this way the subsequent decoding of the latent representations into per-point features is conditioned on the respective other point cloud, and thus can predict which points are not only salient, but also lie in the overlap region between the two point clouds. The ability to focus on points that are relevant for matching greatly improves performance: PREDATOR raises the rate of successful registrations by more than 20 state of the art for the 3DMatch benchmark with 89 code and pre-trained models will be available at https://github.com/ShengyuH/OverlapPredator.

READ FULL TEXT

page 4

page 8

page 15

page 16

research
07/02/2022

ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairs

Low-overlap regions between paired point clouds make the captured featur...
research
07/22/2023

Pyramid Semantic Graph-based Global Point Cloud Registration with Low Overlap

Global point cloud registration is essential in many robotics tasks like...
research
07/05/2023

GAFAR: Graph-Attention Feature-Augmentation for Registration A Fast and Light-weight Point Set Registration Algorithm

Rigid registration of point clouds is a fundamental problem in computer ...
research
01/15/2020

Learning multiview 3D point cloud registration

We present a novel, end-to-end learnable, multiview 3D point cloud regis...
research
08/11/2022

PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees

Being able to learn an effective semantic representation directly on raw...
research
02/28/2023

A Unified BEV Model for Joint Learning of 3D Local Features and Overlap Estimation

Pairwise point cloud registration is a critical task for many applicatio...
research
02/28/2023

PCR-CG: Point Cloud Registration via Deep Color and Geometry

In this paper, we introduce PCR-CG: a novel 3D point cloud registration ...

Please sign up or login with your details

Forgot password? Click here to reset