AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Learning With Noisy Labels for Robust Point Cloud Segmentation

Shuquan Ye, Dongdong Chen, Songfang Han, Jing Liao

ICCV 2021 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 53 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 cluster-level voting for label correction (ablation)PNAL (DGCNN) · S3DIS, 60% symmetric noiseOA: 0.8011 -> 0.8236Improved
use gamma=1 (most greedy winner label) instead of gamma=4 (ablation)PNAL (DGCNN) · S3DIS, 60% symmetric noiseOA: 0.8110 vs 0.8236No clear effect
use gamma=2 instead of gamma=4 (ablation)PNAL (DGCNN) · S3DIS, 60% symmetric noiseOA: 0.8209 vs 0.8236No clear effect
increase history length q to 8 (with E_warm-up=8) (ablation)PNAL (DGCNN) · S3DIS, 60% symmetric noiseOA: 0.8236 -> 0.7704Hurt
use ground-truth instances instead of clustering (ablation)PNAL (DGCNN) · S3DIS, 60% symmetric noiseOA: 0.8236 -> 0.8287Improved
increase E_warm-up from 5 to 8 (ablation)PNAL (DGCNN) · S3DIS, 60% symmetric noiseOA: 0.8236 -> 0.7851Hurt
increase E_warm-up from 5 to 11 (ablation)PNAL (DGCNN) · S3DIS, 20% symmetric noiseOA: 0.8569 -> 0.8343Hurt
increase E_warm-up from 5 to 11 (ablation)PNAL (DGCNN) · S3DIS, 40% symmetric noiseOA: 0.8378 -> 0.8009Hurt
use DBSCAN eps=0.015 or 0.021 instead of 0.018 (ablation)PNAL (DGCNN) · S3DIS, 60% symmetric noiseOA: 0.8206 / 0.8159 vs 0.8236No clear effect
use GMM or spectral clustering instead of DBSCAN eps=0.018 (ablation)PNAL (DGCNN) · S3DIS, 60% symmetric noiseOA: 0.8178 / 0.8162 vs 0.8236No clear effect
add PNAL to DGCNNDGCNN+CE · S3DIS, 60% symmetric noiseOA: 0.6390 -> 0.8236Improved
add PNAL to DGCNN under clean labelsDGCNN+CE · S3DIS, 0% noiseOA: 0.8692 -> 0.8686No clear effect

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