AI Paper Atlas

Research map / Point clouds / Registration and matching

ERNet: Efficient Non-Rigid Registration Network for Point Sequences

Guangzhao He, Yuxi Xiao, Zhen Xu, Xiaowei Zhou, Sida Peng

ICCV 2025 · Point clouds › Registration and matching · approach: Non-rigid point set registration · 1 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 node-graph skinning instead of dense matching (ablation)ERNet · D-FAUST test (ablation)ATE_3D: 0.014 -> 0.011Improved
add node-graph skinning instead of dense matching (ablation)ERNet · D-FAUST test (ablation)delta_0.05: 0.885 -> 0.918Improved
add node-graph skinning instead of dense matching (ablation)ERNet · D-FAUST test (ablation)T_avg (s/frame): 4.645 -> 0.172Improved
add node-to-frame matching network phi (ablation)ERNet · D-FAUST test (ablation)ATE_3D: 0.022 -> 0.011Improved
add node-to-frame matching network phi (ablation)ERNet · D-FAUST test (ablation)delta_0.01: 0.289 -> 0.416Improved
add node-to-frame matching network phi (ablation)ERNet · D-FAUST test (ablation)T_avg (s/frame): 0.060 -> 0.172Hurt
add spatio-temporal refinement transformer Phi (ablation)ERNet · D-FAUST test (ablation)ATE_3D: 0.014 -> 0.011Improved
add spatio-temporal refinement transformer Phi (ablation)ERNet · D-FAUST test (ablation)delta_0.01: 0.366 -> 0.416Improved
add spatio-temporal refinement transformer Phi (ablation)ERNet · D-FAUST test (ablation)delta_0.05: 0.889 -> 0.918Improved
reduce inference update iterations from M=6 to M=4 (ablation)ERNet · D-FAUSTATE_3D: M=6 to M=4, minor performance dropNo clear effect
use B=256 graph nodes (ablation)ERNet · D-FAUSTATE_3D: B=256 chosen as best balance of accuracy and efficiencyImproved
replace chained per-sequence optimization baseline C-NDP with ERNetC-NDP · D-FAUST testATE_3D: 0.041 -> 0.016Improved

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