3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

Gim Hee Lee; Zi Jian Yew

3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1807.09413 v1 pith:LOQV25HJ submitted 2018-07-25 cs.CV

Zi Jian Yew , Gim Hee Lee This is my paper

classification cs.CV

keywords pointdfeat-netclouddatasetsfeaturematchingalignmentannotation

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

In this paper, we propose the 3DFeat-Net which learns both 3D feature detector and descriptor for point cloud matching using weak supervision. Unlike many existing works, we do not require manual annotation of matching point clusters. Instead, we leverage on alignment and attention mechanisms to learn feature correspondences from GPS/INS tagged 3D point clouds without explicitly specifying them. We create training and benchmark outdoor Lidar datasets, and experiments show that 3DFeat-Net obtains state-of-the-art performance on these gravity-aligned datasets.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

SHReg: Strictly Rotation-Equivariant Point Cloud Registration via Spherical Harmonics
cs.CV 2026-07 conditional novelty 5.0 of 10

A rotation-equivariant registration network whose per-correspondence closed-form pose hypotheses improve 3D match accuracy, especially under large rotations.

Pith tools