AI Paper Atlas

Research map / Point clouds / Point cloud classification

Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective

Ziwei Zhang, Xin Yue Wang, Zeyang Zhang, Peng Cui, Wenwu Zhu

TPAMI 2025 · Point clouds › Point cloud classification · approach: Equivariant point cloud networks

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
replace raw coordinates with TinvNet initial representationPointNet · ModelNet40 z/SO3accuracy (%): 13.4 -> 86.2Improved
replace raw coordinates with TinvNet initial representationDGCNN · ModelNet40 z/SO3accuracy (%): 22.3 -> 89.5Improved
replace raw coordinates with TinvNet representationDGCNN · ModelNet40 z/zaccuracy (%): 92.2 -> 89.5Hurt
replace raw coordinates with TinvNet representationPointNet · ShapeNet z/SO3mean IoU (%): 29.0 -> 80.0Improved
add TinvNet to GATGAT · TSP-100 translationroute length: 52.15 -> 8.52Improved
add TinvNet to GATGAT · CVRP-100 translationroute length: 104.23 -> 17.31Improved
add TinvNet to GATGAT · TSP-100 no transformationroute length: 8.49 -> 8.52No clear effect
add TinvNet to GATGAT · CVRP-100 no transformationroute length: 17.73 -> 17.31Improved
replace TinvNet representation with k-NN distances (ablation)PointNet · ModelNet40 z/SO3accuracy (%): 86.2 -> 24.9Hurt
replace TinvNet representation with PCA whitening (ablation)DGCNN · ModelNet40 z/SO3accuracy (%): 89.5 -> 85.8Hurt
enumerate 2^d eigenvector signs as augmentation instead of canonical sign (ablation)TinvNet(PointNet) · ModelNet40 z/SO3accuracy (%): 85.4 -> 86.2Improved
enumerate 2^d eigenvector signs instead of canonical sign (ablation)TinvNet(DGCNN) · ModelNet40 z/zaccuracy (%): 88.3 -> 89.5Improved

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