AI Paper Atlas

Research map / Point clouds / Registration and matching

DeepGMR: Learning Latent Gaussian Mixture Models for Registration

Wentao Yuan, Benjamin Eckart, Kihwan Kim, Varun Jampani, Dieter Fox, Jan Kautz

ECCV 2020 · Point clouds › Registration and matching · approach: Learned feature-based registration · 284 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
learned latent GMM correspondences (DeepGMR) instead of point-to-point matching (DCP) on unseen categoriesDeepGMR vs DCP · ModelNet unseenRMSE: 0.34 -> 0.01Improved
learned latent GMM correspondences instead of point-to-point matching (DCP) on real scansDeepGMR vs DCP · ICL-NUIMRecall@0.2: 0.16 -> 0.99Improved
add sensor-like noise to source and target independentlyDCP · ModelNet clean to noisyRMSE: 0.02 -> 0.08Hurt
add independent noise to source and targetDeepGMR · ModelNet clean to noisyRMSE: 0.00 -> 0.01No clear effect
probabilistic latent matching instead of exhaustive search (TEASER++) for speedDeepGMR vs TEASER++ · ModelNet40 runtimetime per instance: 13.3s -> 11msImproved
use more GMM components J beyond 16 (ablation)DeepGMR · ModelNet noisyRMSE CDFNo clear effect
add RRI rotation-invariant input features instead of raw xyz (ablation)DeepGMR · ModelNet noisyRMSE CDFImproved
train with RMSE metric loss instead of simple MSE loss (ablation)DeepGMR · ModelNet noisyRMSE CDFNo clear effect
test with 4 times denser point clouds without finetuningDeepGMR · ModelNet noisyRMSE CDFNo clear effect
test with 4 times sparser point clouds without finetuningDeepGMR · ModelNet noisyRMSE CDFHurt
increase FGR input points to 4096 on clean dataFGR · ModelNet cleanRMSE: 0.19 -> 0.04Improved
increase FGR input points to 4096 on noisy dataFGR · ModelNet noisyRMSE: 0.2 -> 0.22No clear effect

Later papers that compared with this method

4 later accepted papers report DeepGMR as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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