What Stops Learning-based 3D Registration from Working in the Real World?

11/19/2021
by   Zheng Dang, et al.
EPFL
Xi'an Jiaotong University
0

Much progress has been made on the task of learning-based 3D point cloud registration, with existing methods yielding outstanding results on standard benchmarks, such as ModelNet40, even in the partial-to-partial matching scenario. Unfortunately, these methods still struggle in the presence of real data. In this work, we identify the sources of these failures, analyze the reasons behind them, and propose solutions to tackle them. We summarise our findings into a set of guidelines and demonstrate their effectiveness by applying them to different baseline methods, DCP and IDAM. In short, our guidelines improve both their training convergence and testing accuracy. Ultimately, this translates to a best-practice 3D registration network (BPNet), constituting the first learning-based method able to handle previously-unseen objects in real-world data. Despite being trained only on synthetic data, our model generalizes to real data without any fine-tuning, reaching an accuracy of up to 67

READ FULL TEXT

page 6

page 7

page 8

03/29/2022

Learning-based Point Cloud Registration for 6D Object Pose Estimation in the Real World

In this work, we tackle the task of estimating the 6D pose of an object ...
06/08/2020

Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration

While 3D-3D registration is traditionally tacked by optimization-based m...
03/28/2021

ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning

Point cloud registration is a common step in many 3D computer vision tas...
10/27/2019

PRNet: Self-Supervised Learning for Partial-to-Partial Registration

We present a simple, flexible, and general framework titled Partial Regi...
11/23/2020

3D Registration for Self-Occluded Objects in Context

While much progress has been made on the task of 3D point cloud registra...
08/31/2023

Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learning

We present Point-TTA, a novel test-time adaptation framework for point c...
06/07/2021

FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration

Data association is important in the point cloud registration. In this w...

Please sign up or login with your details

Forgot password? Click here to reset