AI Paper Atlas

Research map / Point clouds / Shape and surface completion

AdaFit: Rethinking Learning-Based Normal Estimation on Point Clouds

Runsong Zhu, Yuan Liu, Zhen Dong, Yuan Wang, Tengping Jiang, Wenping Wang, Bisheng Yang

ICCV 2021 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 62 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 offset prediction (ablation)weighted surface fitting (n=3) · PCPNet averagenormal angle RMSE (degrees): 12.33 -> 11.22Improved
add offset prediction (ablation)weighted surface fitting (n=1) · PCPNet averagenormal angle RMSE (degrees): 12.54 -> 11.24Improved
add offset prediction (ablation)weighted surface fitting (n=2) · PCPNet averagenormal angle RMSE (degrees): 13.73 -> 11.26Improved
add offset prediction (ablation)weighted surface fitting (n=3) · PCPNet no noisenormal angle RMSE (degrees): 7.91 -> 6.00Improved
add offset prediction (ablation)weighted surface fitting (n=3) · PCPNet high noisenormal angle RMSE (degrees): 21.48 -> 21.76No clear effect
add offset prediction (ablation)weighted surface fitting (n=2) · PCPNet varying density (strips)normal angle RMSE (degrees): 12.00 -> 7.18Improved
add offset prediction makes performance insensitive to polynomial order (ablation)weighted surface fitting · PCPNet averagenormal angle RMSE (degrees): 13.73 vs 11.26 at n=2Improved
add CSA layers (scale 700) (ablation)AdaFit with offsets · PCPNet averagenormal angle RMSE (degrees): 11.22 -> 10.76Improved
use smaller neighborhood scale 256 instead of 700 without CSA (ablation)AdaFit with offsets · PCPNet averagenormal angle RMSE (degrees): 11.22 -> 11.02Mixed
truncate low-weight points (threshold 0.05) instead of offset prediction (ablation)weighted fitting · PCPNet averagenormal angle RMSE (degrees): 11.95 vs offset 11.22Hurt
truncate points with threshold 0.50 (ablation)weighted fitting · PCPNet averagenormal angle RMSE (degrees): 12.33 -> 13.18Hurt
use AdaFit instead of DeepFitDeepFit · SceneNNnormal angle RMSE (degrees): 18.33 -> 16.25Improved

Later papers that compared with this method

5 later accepted papers report AdaFit as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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