AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation

Qing Li, Huifang Feng, Kanle Shi, Yue Gao, Yi Fang, Yu-Shen Liu, Zhizhong Han

TPAMI 2024 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 18 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 patch encoding (ablation)SHS-Net · PCPNet oriented normalavg RMSE: 45.80 -> 19.79Improved
add shape encoding (global latent code) (ablation)SHS-Net · PCPNet oriented normalavg RMSE: 76.37 -> 19.79Improved
add distance-based weight w (ablation)SHS-Net · PCPNet oriented normalavg RMSE: 22.00 -> 19.79Improved
add attention-weighted normal prediction module H (ablation)SHS-Net · PCPNet oriented normalavg RMSE: 23.11 -> 19.79Improved
regress unoriented normal and sign separately with L_sin and L_sgn (ablation)SHS-Net · PCPNet oriented normalavg RMSE: 33.29 -> 19.79Improved
add neighbor normal weighted MSE loss (ablation)SHS-Net · PCPNet oriented normalavg RMSE: 30.99 -> 19.79Improved
add density-gradient term to point sampling (ablation)SHS-Net · PCPNet oriented normalavg RMSE: 24.07 -> 19.79Improved
add random-sample term to point sampling (ablation)SHS-Net · PCPNet oriented normalavg RMSE: 21.54 -> 19.79Improved
change random-sample ratio from 1/1.5 to 1/3 (ablation)SHS-Net · PCPNet oriented normalavg RMSE: 19.79 -> 23.05Hurt
use 1100 instead of 1200 shape points (ablation)SHS-Net · PCPNet oriented normalavg RMSE: 19.79 -> 21.69Hurt
use unoriented pipeline Ours-U instead of oriented model for unoriented normalsSHS-Net · PCPNet unoriented normalavg RMSE: 9.96 -> 9.55Improved
re-orient unoriented normals with NGL module instead of own oriented normalsSHS-Net · PCPNet oriented normalavg RMSE: 19.79 -> 18.29Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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