AI Paper Atlas

Research map / Point clouds / Point cloud classification

Spatial Transformer for 3D Point Clouds

Jiayun Wang, Rudrasis Chakraborty, Stella X. Yu

TPAMI 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 42 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 deformable spatial transformersDGCNN edge convolution · ModelNet40 classificationaccuracy: 88.8 -> 89.9Improved
add deformable spatial transformers with random input rotationsDGCNN · ModelNet40 (random rotations)accuracy: 85.7 -> 88.3Improved
add deformable spatial transformers to SplatNetSplatNet · ModelNet40 classificationaccuracy: 86.3 -> 88.6Improved
add deformable spatial transformersDGCNN · ShapeNet part segmentationmIoU: 84.2 -> 85.3Improved
add projective transformers instead of affine (ablation)DGCNN · ShapeNet part segmentationmIoU: 84.7 -> 84.4Hurt
add deformable transformers to PointCNNPointCNN · ShapeNet part segmentationmIoU: 84.9 -> 85.8Improved
add deformable transformersSplatNet · ShapeNet part segmentationmIoU: 84.6 -> 85.2Improved
add deformable transformersDGCNN · S3DISmIoU: 56.0 -> 57.2Improved
add deformable transformersVoxelNet · KITTI car 3D EasyAP: 45.7 -> 46.1Improved
update transformation matrices end-to-end instead of random fixed (ablation)Deformable transformer · ShapeNet part segmentationmIoU: 84.7 -> 85.3Improved
add more graphs per layer (1 to 4) at fixed sub-feature dim 32 (ablation)Deformable transformer · ShapeNet part segmentationmIoU: 84.9 -> 85.3Improved
add more graphs at fixed total dim 64 (1 to 4) (ablation)Deformable transformer · ShapeNet part segmentationmIoU: 85.3 -> 83.5Hurt

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