AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation

Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia

ICCV 2019 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 223 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
use concatenation as edge function instead of subtraction (ablation)Point-Edge network · ScanNet v2 valmIoU: 58.31 -> 63.36Improved
use concatenation as edge function instead of summation (ablation)Point-Edge network · ScanNet v2 valmIoU: 57.86 -> 63.36Improved
use concatenation as edge function instead of Hadamard product (ablation)Point-Edge network · ScanNet v2 valmIoU: 59.07 -> 63.36Improved
use plain concatenation instead of ConcatSub edge function (ablation)Point-Edge network · ScanNet v2 valmIoU: 63.09 -> 63.36No clear effect
use concatenation as edge function instead of subtraction (ablation)Point-Edge network · S3DIS Area 5mIoU: 58.85 -> 61.85Improved
use concatenation as edge function instead of ConcatSub (ablation)Point-Edge network · S3DIS Area 5mIoU: 59.37 -> 61.85Improved
use max-pooling plus concatenation for message passing instead of AdaAggre with softmax (ablation)Point-Edge network · ScanNet v2 valmIoU: 56.44 -> 63.36Improved
use max-pooling plus concatenation instead of AdaAggre without softmax (ablation)Point-Edge network · ScanNet v2 valmIoU: 55.01 -> 63.36Improved
add softmax to adaptive aggregation weights (ablation)AdaAggre message passing · ScanNet v2 valmIoU: 55.01 -> 56.44Improved
add hierarchical graph construction with edge upsampling (ablation)Point-Edge network · ScanNet v2 valmIoU: 57.01 -> 63.36Improved
add hierarchical graph construction with edge upsampling (ablation)Point-Edge network · ScanNet v2 valmAcc: 66.52 -> 72.61Improved
add hierarchical graph construction with edge upsampling (ablation)Point-Edge network · ScanNet v2 valOA: 83.57 -> 86.13Improved

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