AI Paper Atlas

Research map / Point clouds / Registration and matching

A Robust Loss for Point Cloud Registration

Zhi Deng, Yuxin Yao, Bailin Deng, Juyong Zhang

ICCV 2021 · Point clouds › Registration and matching · approach: Robust inlier selection for registration · 34 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace Chamfer distance with the line-intersection metricoptimization-based registration · Human (optimization-based)rotation error (degrees): 5.863 -> 0.576Improved
add Welsch robust function to Chamfer distance (nu0=0.5)Chamfer distance · Human (optimization-based)rotation error (degrees): 5.863 -> 4.84Improved
use convex combination of candidate points for intersection instead of all candidates (ablation)line-intersection metric · Human (optimization-based)rotation error (degrees): 49.27 -> 0.576Improved
sample random lines uniformly instead of bounding-box sampling (Sample1) (ablation)line-intersection metric · Human (optimization-based)rotation error (degrees): 20.482 -> 0.576Improved
sample random lines uniformly instead of perturbed point sampling (Sample2) (ablation)line-intersection metric · Human (optimization-based)rotation error (degrees): 5.201 -> 0.576Improved
set nu0 to 0.5 instead of 1 (ablation)line-intersection metric · Human (optimization-based)rotation error (degrees): 2.814 -> 0.576Improved
set nu0 to 0.5 instead of 0.01 or 100 (ablation)line-intersection metric · Human (optimization-based)rotation error (degrees): 10.814 / 7.786 -> 0.576Improved
use our metric instead of Chamfer distance as unsupervised lossDCP · Airplanerotation error (degrees): 6.612 -> 3.808Improved
use our metric instead of Chamfer distance as unsupervised lossFMR · Real dataset (unlabeled)rotation error (degrees): 7.559 -> 3.263Improved
use our metric instead of Chamfer distance as unsupervised lossRPM-Net · Real dataset (unlabeled)rotation error (degrees): 11.28 -> 2.972Improved
unsupervised our metric instead of ground-truth supervisionRPM-Net · Airplanerotation error (degrees): 2.19 -> 1.673Improved
unsupervised our metric instead of ground-truth supervisionDCP · Human (learning-based)rotation error (degrees): 3.841 -> 4.841Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy