AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Vector Neurons: A General Framework for SO(3)-Equivariant Networks

Congyue Deng, Or Litany, Yueqi Duan, Adrien Poulenard, Andrea Tagliasacchi, Leonidas J. Guibas

ICCV 2021 · Architectures and efficiency › CNN design · approach: Group symmetry equivariant networks · 265 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
replace PointNet with VN-PointNetPointNet · ModelNet40 (z/SO(3))accuracy: 19.6 -> 77.5Improved
replace DGCNN with VN-DGCNNDGCNN · ModelNet40 (z/SO(3))accuracy: 33.8 -> 89.5Improved
replace DGCNN with VN-DGCNN under full rotation augmentationDGCNN · ModelNet40 (SO(3)/SO(3))accuracy: 88.6 -> 90.2Improved
replace DGCNN with VN-DGCNNDGCNN · ShapeNet-part (z/SO(3))mIoU: 49.3 -> 81.4Improved
train on aligned data, test on arbitrary rotations: VN-DGCNN vs DGCNNDGCNN · ModelNet40 (I/SO(3))accuracy: 16.6 -> 90.0Improved
train on aligned data, test on arbitrary rotations: VN-PointNet vs PointNetPointNet · ShapeNet-part (I/SO(3))mIoU: 30.3 -> 73.0Improved
use equivariant VN-PointNet encoder in OccNetOccNet · ShapeNet reconstruction (SO(3)/SO(3))volumetric mIoU: 58.2 -> 68.8Improved
use equivariant VN-PointNet encoder in OccNet on aligned dataOccNet · ShapeNet reconstruction (I/I)volumetric mIoU: 71.4 -> 69.3Hurt
add invariant decoder with standard PointNet encoder (ablation)OccNet · ShapeNet reconstruction (I/I)volumetric mIoU: 71.4 -> 72.0Improved
use detached linear and non-linear layers in VN-DGCNN (ablation)VN-DGCNN · ModelNet40 (z/z)accuracy: 89.5 -> 90.8Improved
use detached linear and non-linear layers in VN-PointNet (ablation)VN-PointNet · ModelNet40accuracy: 77.5 -> 78.2 (z/z); 77.2 -> 76.8 (SO(3)/SO(3))Mixed
use mean pooling instead of VN-MAX pooling in VN-DGCNN (ablation)VN-DGCNN · ModelNet40 (z/z)accuracy: 88.9 -> 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