AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds

Haoran Zhou, Honghua Chen, Yingkui Zhang, Mingqiang Wei, Haoran Xie, Jun Wang, Tong Lü, Jing Qin, Xiao-Ping Steven Zhang

TPAMI 2022 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 59 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 Refine-Net refinement on MFPS initial normalsMFPS · Wang et al. syntheticmean angular error: 4.75 -> 3.87Improved
add Refine-Net refinement on Nesti-Net normalsNesti-Net · Wang et al. syntheticmean angular error: 4.55 -> 4.11Improved
add Refine-Net refinement on PCPNet-ms normalsPCPNet-ms · Wang et al. syntheticmean angular error: 7.06 -> 5.64Improved
add fitting patch selection to MFPS (ablation)MFPS · Wang et al. syntheticmean angular error: 5.76 -> 4.75Improved
add point and height-map feature modules to normals (ablation)Refine-Net · Wang et al. syntheticmean angular error: 4.40 -> 3.87Improved
add point module to normals&HMPs (ablation)Refine-Net · Wang et al. syntheticmean angular error: 4.31 -> 3.87Improved
add height-map module to normals&points (ablation)Refine-Net · Wang et al. syntheticmean angular error: 3.97 -> 3.87Improved
use weight matrix connection instead of concatenation (ablation)Refine-Net · Wang et al. syntheticmean angular error: 4.04 -> 3.87Improved
use weight matrix connection instead of residual (ablation)Refine-Net · Wang et al. syntheticmean angular error: 4.03 -> 3.87Improved
use weight matrix instead of translation matrix (ablation)Refine-Net · Wang et al. syntheticmean angular error: 3.95 -> 3.87Improved
use L2 instead of L1 loss (ablation)Refine-Net · PCPNet dataset (noise 0.012)angular RMS error: 23.50 -> 22.57Improved
use L2 instead of L1 loss (ablation)Refine-Net · PCPNet dataset (noise none)angular RMS error: 6.05 -> 6.27Hurt

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