PointCloudLibrary / PointCloudLibrary/pcl

2D IterativeClosestPointWithNormals

Open
#2,377 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

status: stale
Dominant language
C++
Stars
11.1k
Forks
4.7k
Avg merge
4d 10h
Merged PRs (30d)
6

Description

Hi,

I just figured that if you try to use the IterativeClosestPointWithNormals with 2D point cloud, it will fail.
In the Transformation Estimation PointToPlaneLLS, the a and b will be 0 (because nz = 0 and sz = 0) and ATA matrix will be :

    //    0 0 0 0 0 0
    //    0 0 0 0 0 0
    //    0 0 X X X 0
    //    0 0 X X X 0
    //    0 0 X X X 0
    //    0 0 0 0 0 0

and won't be inversible (you'll have full of NaN).

In my case, I replaced ATA.setZero() to ATA.setIdentity(), and it works well :)

Best,
Clément

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating IterativeClosestPointWithNormals and the Transformation Estimation PointToPlaneLLS implementation, then reproduce the failure with a 2D point cloud. Inspect how the ATA matrix is initialized and verify the chosen handling prevents NaN results while preserving the existing 3D behavior. Done means 2D ICP with normals completes successfully without an invalid matrix result.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
computer-vision
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.