AI Paper Atlas

Research map / Point clouds / Point cloud classification

CN: Channel Normalization For Point Cloud Recognition

Zetong Yang, Yanan Sun, Shu Liu, Xiaojuan Qi, Jiaya Jia

ECCV 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 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 channel normalization (SSG)PointNet++ · ModelNet40accuracy (%): 90.7 -> 92.9Improved
add channel normalization (MSG)PointNet++ · ModelNet40accuracy (%): 90.7 -> 93.3Improved
use CN instead of RS-CNN fusion (SSG)PointNet++ SSG · ModelNet40accuracy (%): 92.2 -> 92.9Improved
add channel normalization to SA layersPointNet++ · ShapeNet part segmentationclass mIoU (%): 81.9 -> 83.9Improved
add two long-range skip connections to CN (CN2)CN · ShapeNet part segmentationclass mIoU (%): 83.9 -> 84.3Improved
add channel normalization3DSSD · KITTI test Car AP_3D EasyAP (%): 88.36 -> 90.55Improved
add channel normalization3DSSD · KITTI test Car AP_BEV EasyAP (%): 92.66 -> 94.51Improved
add channel normalization3DSSD · KITTI test Car AP_BEV HardAP (%): 85.86 -> 85.86No clear effect
add channel normalization3DSSD · KITTI test Car AP_3D ModerateAP (%): 79.57 -> 79.89Improved
use CN instead of RS-CNN fusion layers3DSSD · KITTI val Car Moderate3D mAP (%): 82.88 -> 85.01Improved
use CN instead of PointNet++ SA layers3DSSD · KITTI val Car Moderate3D mAP (%): 82.37 -> 85.01Improved
add learnable condition parameters alpha1 and alpha2 to CN (ablation)3DSSD + CN · KITTI val Car Moderate3D mAP (%): 84.60 -> 85.01Improved

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