AI Paper Atlas

Research map / Point clouds / Segmentation and detection

JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds

Zeyu Hu, Mingmin Zhen, Xuyang Bai, Hongbo Fu, Chiew-lan Tai

ECCV 2020 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 141 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 the edge stream with naive combination to the segmentation stream (ablation)JSENet segmentation stream · S3DIS Area-5mIoU (%): 64.7 -> 66.2Improved
add the joint refinement module (ablation)JSENet segmentation · S3DIS Area-5mIoU (%): 66.2 -> 67.7Improved
add the joint refinement module (ablation)JSENet edge detection · S3DIS Area-5mMF (ODS) (%): 30.5 -> 31.0Improved
naively combine segmentation stream with edge stream (ablation)JSENet edge detection · S3DIS Area-5mMF (ODS) (%): 30.2 -> 30.5Improved
add enhanced feature extraction to the edge stream (ablation)edge stream · S3DIS Area-5mMF (ODS) (%): 29.4 -> 29.9Improved
add hierarchical supervision to the edge stream (ablation)edge stream · S3DIS Area-5mMF (ODS) (%): 29.9 -> 30.2Improved
use L_bce for first three layers and L_seg for last two instead of L_bce for all five (ablation)hierarchical supervision · S3DIS Area-5mMF (ODS) (%): 30.1 -> 30.2Improved
add the dual semantic edge loss (ablation)JSENet · S3DIS Area-5F-score (%): 22.7 -> 23.1Improved
JSENet joint training versus KPConv aloneKPConv rigid · S3DIS Area-5mIoU (%): 65.4 -> 67.7Improved
use JSENet instead of KPConv for edge detectionedge detection · ScanNetmMF (ODS) (%): 34.8 -> 37.3Improved
use extended CASENet architecture instead of KPConv for 3D edge detectionedge detection · S3DIS Area-5mMF (ODS) (%): 29.4 -> 27.1Hurt

Later papers that compared with this method

2 later accepted papers report JSENet as a baseline in their results tables; 2 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 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