AI Paper Atlas

Research map / Point clouds / Shape and surface completion

PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling

Yue Qian, Junhui Hou, Sam Kwong, Ying He

ECCV 2020 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 152 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 feature recalibration (ablation)PUGeo-Net · Ablation (R=8 as stated)CD (x10^-2): 0.325 -> 0.323Improved
add normal prediction and supervision (ablation)PUGeo-Net · Ablation (R=8 as stated)CD (x10^-2): 0.331 -> 0.323; HD 2.232 -> 1.011Improved
add learned adaptive 2D sampling (ablation)PUGeo-Net · Ablation (R=8 as stated)CD (x10^-2): 0.326 -> 0.323Improved
predict linear transformation instead of direct MLP regression (ablation)PUGeo-Net · Ablation (R=8 as stated)CD (x10^-2): 0.394 -> 0.323; CD# 1.855 -> 0.524Improved
add coarse-to-fine prediction (ablation)PUGeo-Net · Ablation (R=8 as stated)CD (x10^-2): CD 0.330 -> 0.323; HD# 5.241 -> 5.267Mixed
use PUGeo-Net predicted normals instead of PCA with 35 neighboursPUGeo-Net · Normal estimation (R=8)CD# (x10^-2): 0.553 -> 0.549Improved
use PUGeo-Net instead of PU-Net-M (PU-Net predicting 6 outputs)PUGeo-Net · Normal estimation (R=8)CD# (x10^-2): 0.678 -> 0.549Improved
vary PCA neighbourhood size 10 to 35PCA normals · Normal estimation (R=8)CD# (x10^-2): 0.586 -> 0.553Mixed
use PUGeo-Net instead of MPU at 4xPUGeo-Net · Upsampling 4xCD (x10^-2): 0.573 -> 0.558Improved
use PUGeo-Net instead of MPU at 16xPUGeo-Net · Upsampling 16xCD (x10^-2): 0.344 -> 0.323Improved

Later papers that compared with this method

1 later accepted paper reports PUGeo-Net as a baseline in their results tables; 1 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