AI Paper Atlas

Research map / Point clouds / Registration and matching

DeepPRO: Deep Partial Point Cloud Registration of Objects

Donghoon Lee, Onur C. Hamsici, Steven Feng, Prachee Sharma, Thorsten Gernoth

ICCV 2021 · Point clouds › Registration and matching · approach: Learned feature-based registration · 26 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
add point cloud generation network instead of naive global-feature regression (ablation)DeepPRO · Linemod (unseen objects, avg of 11)rotation error (deg): 2.12 -> 1.19Improved
use learned transform estimation network instead of SVD on dense correspondences (ablation)DeepPRO · Linemod (unseen objects, avg of 11)rotation error (deg): 1.94 -> 1.19Improved
add random rotation layer during training (ablation)DeepPRO · Linemod (unseen objects, avg of 11)rotation error (deg): 1.46 -> 1.19Improved
add bidirectional training path (ablation)DeepPRO · Linemod (unseen objects, avg of 11)rotation error (deg): 1.38 -> 1.19Improved
add ADD loss (ablation)DeepPRO · Linemod (unseen objects, avg of 11)rotation error (deg): 1.32 -> 1.19Improved
add ADD loss (ablation)DeepPRO · Linemod (unseen objects, avg of 11)ADD (cm): 0.27 -> 0.22Improved
replace DGCNN encoder with PointNet (ablation)DeepPRO · Linemod (unseen objects, avg of 11)rotation error (deg): 1.19 -> 1.36No clear effect
train with predicted object mask instead of ground truth mask (ablation)DeepPRO · Linemod (unseen objects, avg of 11)rotation error (deg): 1.19 -> 1.32No clear effect
reduce input points from 512 to 256 (ablation)DeepPRO · Linemod (unseen objects, avg of 11)rotation error (deg): 1.19 -> 1.26Hurt
reduce input points from 512 to 128 (ablation)DeepPRO · Linemod (unseen objects, avg of 11)ADD (cm): 0.22 -> 0.32Hurt
use DeepPRO instead of classical ICPDeepPRO · Linemod (unseen objects, avg of 11)rotation error (deg): 2.15 -> 1.19Improved
use DeepPRO instead of PRNet on synthetic ModelNet40PRNet · ModelNet40 (partial, noisy, large baseline)RMSE(R): 4.323 -> 2.617Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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