AI Paper Atlas

Research map / Point clouds / Shape and surface completion

NeAF: Learning Neural Angle Fields for Point Normal Estimation

Shujuan Li, Junsheng Zhou, Baorui Ma, Yu-Shen Liu, Zhizhong Han

AAAI 2023 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 40 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
learn an implicit angle field from random query directions, then select and refine candidate normalsNeAF · PCPNet averageangle RMSE: 10.76 -> 10.22Improved
learn an implicit angle field from random query directions, then select and refine candidate normalsNeAF · SceneNNRMSE: 10.19 -> 9.50Improved
add coarse normal prediction before refinement (ablation)NeAF · PCPNet averageangle RMSE: 38.56 -> 10.22Improved
add coarse normal refinement (ablation)NeAF · PCPNet averageangle RMSE: 10.33 -> 10.22Improved
average the refined coarse normals rather than selecting the one with minimum angle offset (ablation)NeAF · PCPNet averageangle RMSE: 10.25 -> 10.22Improved
use 2.5k rather than 5k training query vectors (ablation)NeAF · PCPNet averageangle RMSE: 10.22 -> 10.27Hurt
use 7.5k rather than 5k training query vectors (ablation)NeAF · PCPNet averageangle RMSE: 10.22 -> 10.28Hurt
use 10k rather than 5k training query vectors (ablation)NeAF · PCPNet averageangle RMSE: 10.22 -> 10.27Hurt
refine 1 rather than 10 coarse normals (ablation)NeAF · PCPNet averageangle RMSE: 10.22 -> 10.26Hurt
refine 5 rather than 10 coarse normals (ablation)NeAF · PCPNet averageangle RMSE: 10.22 -> 10.23Hurt
refine 20 rather than 10 coarse normals (ablation)NeAF · PCPNet averageangle RMSE: 10.22 -> 10.22No clear effect
refine 50 rather than 10 coarse normals (ablation)NeAF · PCPNet averageangle RMSE: 10.22 -> 10.22No clear effect

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