Table 2 Performance on ModelNet and ModelLoNet datasets

From: Enhancing point cloud registration with transformer: cultural heritage protection of the Terracotta Warriors

Method

ModelNet

ModelLoNet

CD

RRE(\( ^{\circ }\))

RTE(m)

CD

RRE(\( ^{\circ }\))

RTE(m)

PointNetLK[43]

0.0235

29.725

0.297

0.0367

48.567

0.507

DCP[44]

0.0117

11.975

0.171

0.0268

16.501

0.3

RPM-Net[45]

0.00085

1.712

0.018

0.005

7.342

0.124

OMNet[37]

0.0015

2.947

0.032

0.0074

6.517

0.129

Predator[29]

0.00089

1.739

0.019

0.0083

5.235

0.132

REGTR[35]

0.00078

1.473

0.014

0.0037

3.93

0.087

UDPReg[39]

0.0306

1.331

0.011

0.0416

3.578

0.069

HECPG [46]

–

1.472

0.016

–

3.371

0.089

Our

0.0006

1.132

0.013

0.0035

1.585

0.124

  1. The best results are in bold
Back to article page