AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Instance-Aware Embedding for Point Cloud Instance Segmentation

Tong He, Yifan Liu, Chunhua Shen, Xinlong Wang, Changming Sun

ECCV 2020 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 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 focal loss to the semantic branch (ablation)PointNet++ two-branch baseline · ScanNetV2 valAP50: 22.0 -> 24.0Improved
add focal loss to the semantic branch (ablation)PointNet++ two-branch baseline · ScanNetV2 valAP25: 45.2 -> 45.5No clear effect
add instance-aware context (IAM) to the instance decoder (ablation)Baseline + FL · ScanNetV2 valAP50: 24.0 -> 27.6Improved
add instance-aware context (IAM) to the instance decoder (ablation)Baseline + FL · ScanNetV2 valAP25: 45.5 -> 48.2Improved
add centroid constraint loss Lcen (ablation)Baseline + FL + InsContext · ScanNetV2 valAP50: 27.6 -> 28.9Improved
add geometric embedding (predicted centroids concatenated to embedding) (ablation)Baseline + FL + InsContext + Lcen · ScanNetV2 valAP50: 28.9 -> 31.5Improved
add geometric embedding (predicted centroids concatenated to embedding) (ablation)Baseline + FL + InsContext + Lcen · ScanNetV2 valAP25: 48.9 -> 50.4Improved
use more representative points than K=18 (ablation)IAM · ScanNetV2 valAP50No clear effect
enlarge the embedding dimension (ablation)discriminative embedding · ScanNetV2 valAP50No clear effect
apply K-NN only at the bottleneck layer (IAM) instead of every point (ASIS)instance segmentation network · training memory per samplememory: 700M -> 400MImproved
apply K-NN only at the bottleneck layer (IAM) instead of every point (ASIS)instance segmentation network · inference time per blocktime: 60ms -> 42msImproved
IAM versus ASIS on ScanNetV2 validationPointNet++ backbone · ScanNetV2 valmAP@0.25: 47.4 -> 50.4Improved

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