activity
20182022
most citedREGTR: End-to-end Point Cloud Correspondences with Transformers

17 citations · 18 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV202217 cited

REGTR: End-to-end Point Cloud Correspondences with Transformers

Zi Jian Yew, Gim Hee Lee

Despite recent success in incorporating learning into point cloud registration, many works focus on learning feature descriptors and continue to rely on nearest-neighbor feature ma…

cs.CV2021

Learning Iterative Robust Transformation Synchronization

Zi Jian Yew, Gim Hee Lee

Transformation Synchronization is the problem of recovering absolute transformations from a given set of pairwise relative motions. Despite its usefulness, the problem remains chal…

cs.CV2021

City-scale Scene Change Detection using Point Clouds

Zi Jian Yew, Gim Hee Lee

We propose a method for detecting structural changes in a city using images captured from vehicular mounted cameras over traversals at two different times. We first generate 3D poi…

cs.CV2020

RPM-Net: Robust Point Matching using Learned Features

Zi Jian Yew, Gim Hee Lee

Iterative Closest Point (ICP) solves the rigid point cloud registration problem iteratively in two steps: (1) make hard assignments of spatially closest point correspondences, and…

cs.CV20191 cited

Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes

Ziquan Lan, Zi Jian Yew, Gim Hee Lee

Outlier feature matches and loop-closures that survived front-end data association can lead to catastrophic failures in the back-end optimization of large-scale point cloud based 3…

cs.CV2018

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

Zi Jian Yew, Gim Hee Lee

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…