AI Paper Atlas

Research map / Point clouds / Registration and matching

Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration

Haobo Jiang, Yaqi Shen, Jin Xie, Jun Li, Jianjun Qian, Jian Yang

ICCV 2021 · Point clouds › Registration and matching · approach: Learned feature-based registration · 46 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 sampling network prior to differentiable CEM (without future reward) (ablation)CEMNet · ModelNet40 unseen categoryMAE(R): 1.8625 -> 0.1781Improved
add sampling network prior to differentiable CEM (without future reward) (ablation)CEMNet · ICL-NUIMMAE(R): 1.8333 -> 0.3345Improved
add sampling network when future reward is used (ablation)CEMNet · ModelNet40 unseen categoryMAE(R): 0.3675 -> 0.0804Improved
add sampling network when future reward is used (ablation)CEMNet · ICL-NUIMMAE(R): 0.8364 -> 0.0211Improved
add ICP-driven future reward to score function (with SN) (ablation)CEMNet · ModelNet40 unseen categoryMAE(R): 0.1781 -> 0.0804Improved
add ICP-driven future reward to score function (with SN) (ablation)CEMNet · ICL-NUIMMAE(R): 0.3345 -> 0.0211Improved
add ICP-driven future reward to score function (without SN) (ablation)CEMNet · ICL-NUIMMAE(t): 0.0023 -> 0.0048Hurt
add CEM planning on top of sampling network (SN alone as DCP-v2) (ablation)Sampling network · ModelNet40 unseen categoryMAE(R): 4.4222 -> 0.1781Improved
increase iterations using future reward M from 0 to 4 (ablation)CEMNet · ModelNet40 unseen categoryMAE(R): 0.1782 -> 0.0470Improved
increase iterations using future reward M from 0 to 4 (ablation)CEMNet · ModelNet40 unseen objectMAE(R): 0.3505 -> 0.1258Improved
increase number of iterations T and candidates N (ablation)CEMNet · ICL-NUIMrotation errorImproved
balance current and future reward weights alpha (ablation)CEMNet · ICL-NUIMrotation errorImproved

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