AI Paper Atlas

Research map / Point clouds / Shape and surface completion

CircNet: Meshing 3D Point Clouds with Circumcenter Detection

Huan Lei, Ruitao Leng, Liang Zheng, Hongdong Li

ICLR 2023 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 3 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
replace candidate-triangle enumeration with single-shot circumcenter detectionCircNet · ABC testtotal runtime/seconds: 37.683 -> 3.316 [0.996]Improved
replace candidate-triangle enumeration with single-shot circumcenter detectionCircNet · MGNCD1 (×10²) ↓: 0.270 -> 0.269Improved
use circumcenter detection and duality to recover trianglesCircNet · FAUSTF1 ↑: 0.995 -> 0.993Hurt
use circumcenter detection and duality to recover trianglesCircNet · ABC testF1 ↑: 0.949 -> 0.950Improved
reduce neighborhood size K from 50 to 25 (ablation)CircNet · ABC hyperparameter studyCD1 (×10²) ↓: 0.284 -> 0.285Hurt
reduce predictions per anchor cell s from 2 to 1 (ablation)CircNet · ABC hyperparameter studyCD2 (×10⁵) ↓: 0.545 -> 0.636Hurt
increase neighborhood size K from 50 to 100 (ablation)CircNet · ABC hyperparameter studyCD1 (×10²) ↓: 0.284 -> 0.284No clear effect
increase neighborhood size K from 50 to 200 (ablation)CircNet · ABC hyperparameter studyCD1 (×10²) ↓: 0.284 -> 0.284No clear effect
increase Gaussian noise levelCircNet · ABC robustnessF1 ↑: 0.908 -> 0.793 -> 0.689Hurt

Later papers that compared with this method

1 later accepted paper reports CircNet as a baseline in their results tables; 0 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 1 of 1 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