AI Paper Atlas

Research map / 3D vision / Face and shape

Field Convolutions for Surface CNNs

Thomas W. Mitchel, Vladimir G. Kim, Michael Kazhdan

ICCV 2021 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 31 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
use field convolutions (FC) instead of HSNsurface CNN · SHREC '11 classificationaccuracy: 96.1% -> 99.2%Improved
use field convolutions (FC) instead of DiffusionNetsurface CNN · SHREC '11 classificationaccuracy: 98.9% -> 99.2%Improved
use field convolutions (FC) instead of HSNsurface CNN · Human body segmentation (composite dataset)accuracy: 91.1% -> 92.9%Improved
use field convolutions (FC) instead of DiffusionNetsurface CNN · Human body segmentation (composite dataset)accuracy: 91.5% -> 92.9%Improved
use field convolutions (FC) instead of MeshWalkersurface CNN · Human body segmentation (composite dataset)accuracy: 92.7% -> 92.9%Improved
use field convolutions (FC) instead of HSN with half the memory footprintsurface CNN · parameters per convolutionparameters per convolution: 28 -> 33Mixed
use FCNet instead of HSN and ACSCNN with raw 3D coordinates inputdense correspondence · FAUST remeshedcorrespondence percentage vs geodesic errorImproved
use FCNet instead of HSN and ACSCNNfeature matching · SHREC 2019 shape correspondenceprecision-recallImproved

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