AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud

Mingye Xu, Zhipeng Zhou, Junhao Zhang, Yu Qiao

AAAI 2021 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 15 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 IAF module (ablation)IAF-Net baseline · S3DIS Area 5mIoU (%): 62.60 -> 64.60Improved
Add IAF module (ablation)IAF-Net · S3DIS Area 5mIoU (%): 62.6 -> 64.6Improved
Replace attentive pooling with max-pooling while removing IAF (ablation)IAF-Net · S3DIS Area 5mIoU (%): 62.6 -> 60.6Hurt
Remove correlations from the no-IAF, max-pooling variant (ablation)IAF-Net · S3DIS Area 5mIoU (%): 60.6 -> 59.9Hurt
Remove the encoder multi-scale strategy (ablation)IAF-Net · S3DIS Area 5mIoU (%): 64.6 -> 59.2Hurt
Use fine-grained-feature local difference alone for mining (ablation)IAF-Net · S3DIS Area 5m-IoU (%): 61.7 -> 64.6Improved
Use original-point local difference alone instead of fine-grained-feature difference (ablation)IAF-Net · S3DIS Area 5m-IoU (%): 64.6 -> 61.7Hurt
Use semantic-prediction local difference alone instead of fine-grained-feature difference (ablation)IAF-Net · S3DIS Area 5m-IoU (%): 64.6 -> 62.1Hurt
Combine all three local differences equally instead of using fine-grained-feature difference alone (ablation)IAF-Net · S3DIS Area 5m-IoU (%): 64.6 -> 63.7Hurt
Add multi-stage supervision (ablation)IAF-Net · S3DIS Area 5m-IoU (%): 57.7 -> 64.6Improved
Add stage-5 supervision to the multi-stage loss (ablation)IAF-Net · S3DIS Area 5m-IoU (%): 61.9 -> 64.6Improved
Use IAF-Net instead of KPConvS3DIS Area 5 · S3DIS Area 5mIoU (%): 67.1 -> 64.6Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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