AI Paper Atlas

Research map / 3D vision / Face and shape

3D Equivariant Graph Implicit Functions

Yunlu Chen, Basura Fernando, Hakan Bilen, Matthias Nießner, Efstratios Gavves

ECCV 2022 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 18 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 multi-scale graph sampling (ablation)GraphONet · Synthetic RoomIoU: 0.859 -> 0.883Improved
add multi-scale graph sampling (ablation)GraphONet · ShapeNetmean IoU: 0.897 -> 0.904Improved
add multi-scale graph sampling (ablation)E-GraphONet · Synthetic RoomIoU: 0.814 -> 0.848Improved
use graph encoder instead of PointNet encoder (ablation)GraphONet · Synthetic RoomIoU: 0.826 -> 0.883Improved
use graph encoder instead of PointNet encoder (ablation)GraphONet · ShapeNetmean IoU: 0.887 -> 0.904Improved
use graph encoder instead of PointNet encoder (ablation)ConvONet-3D · Synthetic RoomIoU: 0.847 -> 0.853No clear effect
use hybrid 50% vector channels instead of pure vector neurons (ablation)VN-ONet-style equivariant model · ShapeNetmIoU: 0.694 -> 0.719Improved
use hybrid 50% vector channels instead of pure vector neurons (ablation)VN-PointNet · ModelNet40mAcc: 0.847 -> 0.856Improved
remove all vector channels (pure scalar) (ablation)equivariant implicit model · ShapeNetmIoU: 0.719 -> 0.408Hurt
add training rotation augmentationGraphONet · ShapeNetIoU: 0.846 -> 0.887Improved
use graph local features instead of grid features (GraphONet vs ConvONet-3D)GraphONet · ShapeNet random rotationIoU: 0.761 -> 0.846Improved
add SO(3) equivariant layersGraphONet · ShapeNet canonicalmean IoU: 0.904 -> 0.890Hurt

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