AI Paper Atlas

Research map / Point clouds / Point cloud classification

Meta Architecture for Point Cloud Analysis

Haojia Lin, Xiawu Zheng, Lijiang Li, Fei Chao, Shanshan Wang, Yan Wang, Yonghong Tian, Rongrong Ji

CVPR 2023 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 113 citations (OpenAlex)

Read the paper

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 explicit position embedding instead of implicit position embedding (ablation)Plain block with max pooling · S3DIS Area 5mIoU (%): 68.0±0.3 -> 69.0±0.3Improved
Use explicit position embedding instead of position pooling (ablation)Plain block with max pooling · S3DIS Area 5mIoU (%): 58.4±0.6 -> 69.0±0.3Improved
Use max pooling rather than position pooling for aggregation with explicit embedding (ablation)Plain-EPE block · S3DIS Area 5mIoU (%): 65.4±0.1 -> 69.0±0.3Improved
Replace vector self-attention with max pooling (ablation)Point Transformer · S3DIS Area 5mIoU (%): 70.5±0.3 -> 70.3±0.2No clear effect
Add a two-layer point-update MLP to the N1P1 configuration (ablation)Plain-EPE block · S3DIS Area 5mIoU (%): 69.0±0.3 -> 69.5±0.3Improved
Add an inverted bottleneck to N1P2 (ablation)Plain-EPE block · S3DIS Area 5mIoU (%): 69.5±0.3 -> 69.7±0.3No clear effect
Use N1P2 rather than N0P2, adding a one-layer neighbor-update MLP (ablation)Plain-EPE block · S3DIS Area 5mIoU (%): 67.8±0.4 -> 69.5±0.3Improved
Use N1P2 rather than N2P0, adding a two-layer point-update MLP and reducing neighbor-update depth (ablation)Plain-EPE block · S3DIS Area 5mIoU (%): 68.7±0.3 -> 69.5±0.3Improved
Scale PointMetaBase-XXL instead of PointNeXt-XLPoint cloud segmentation models · S3DIS 6-FoldmIoU (%): 74.9 -> 77.0Improved
Use PointMetaBase-XXL instead of PointNeXt-XLPoint cloud segmentation models · S3DIS Area-5mIoU (%): 70.5±0.3 -> 71.3±0.7Improved
Use PointMetaBase-S instead of PointNeXt-SPoint cloud classification models · ScanObjectNN PB_T50_RSOA (%): 87.7±0.4 -> 87.9±0.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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