AI Paper Atlas

Research map / Point clouds / Point cloud classification

Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis

Qijian Zhang, Junhui Hou, Yue Qian, Yiming Zeng, Juyong Zhang, Ying He

TPAMI 2023 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 55 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 CSConv regional embedding (ablation)FlatNet-Cls-P · ModelNet40 classificationOA (%): 90.5 -> 92.6Improved
add CSConv regional embedding (ablation)FlatNet-Cls-D · ModelNet40 classificationOA (%): 92.2 -> 93.4Improved
use CSConv instead of kxk conv (ablation)FlatNet-Cls-P · ModelNet40 classificationOA (%): 90.9 -> 92.6Improved
use CSConv instead of kxk conv (ablation)FlatNet-Cls-D · ModelNet40 classificationOA (%): 92.5 -> 93.4Improved
add CSConv regional embedding (ablation)FlatNet-Seg-P · ShapeNetPart part segmentationmIoU (%): 84.1 -> 84.9Improved
add CSConv regional embedding (ablation)FlatNet-Seg-D · ShapeNetPart part segmentationmIoU (%): 85.2 -> 85.8Improved
use CSConv instead of kxk conv (ablation)FlatNet-Seg-P · ShapeNetPart part segmentationmIoU (%): 84.5 -> 84.9Improved
use CSConv instead of kxk conv (ablation)FlatNet-Seg-D · ShapeNetPart part segmentationmIoU (%): 85.5 -> 85.8Improved
replace PointNet-vanilla input with PGI representationPointNet-vanilla · ModelNet40 classificationOA (%): 87.1 -> 92.6Improved
replace DGCNN input with PGI representationDGCNN · ModelNet40 classificationOA (%): 92.9 -> 93.4Improved
use PGIs instead of equirectangular spherical parameterizationFlatNet-Cls · ModelNet40 classificationOA (%): 88.5 -> 92.6Improved
use PGIs instead of equirectangular spherical parameterization (stronger variant)FlatNet-Cls · ModelNet40 classificationOA (%): 90.1 -> 93.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 4 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