Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds

About

In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-view pooling module to attentively fuse convolutional features across views. Extensive experiments on existing 3D registration benchmarks show that our method outperforms existing local descriptors both quantitatively and qualitatively.

Lei Li, Siyu Zhu, Hongbo Fu, Ping Tan, Chiew-Lan Tai• 2020

Related benchmarks

TaskDatasetResultRank
Point cloud registration3DMatch (test)--
339
Feature Matching3DMatch (Origin)
STD2.8
33
Feature MatchingETH dataset (test)
FMR (Gazebo Summer)85.3
23
Descriptor matching3DMatch Rotated--
18
3D local descriptor matching3DMatch
Average Recall97.5
16
Feature Matching3DMatch
FMR (tau_2=0.05)97.5
15
Point cloud registration3DMatch Origin v1
Registration Recall82.5
12
Feature Matching3DMatch Rotated (test)
FMR0.969
12
Point cloud registration3DLoMatch v1 (Origin)
Registration Recall41.3
11
Point cloud registration3DLoMatch Rotated v1
Registration Recall40.1
11
Showing 10 of 18 rows

Other info

Follow for update