AI Paper Atlas

Research map / 3D vision / Face and shape

Surface Networks via General Covers

Niv Haim, Nimrod Segol, Heli Ben-Hamu, Haggai Maron, Yaron Lipman

ICCV 2019 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 56 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 covering-map toric image representation instead of octahedron unfolding for spherical signalsInception v3 on ModelNet40 (rot z) · ModelNet40 classificationaccuracy (%): 90.2% -> 91.0%Improved
use covering-map toric image representation instead of equirectangular projection for spherical signalsInception v3 on ModelNet40 (rot z) · ModelNet40 classificationaccuracy (%): 90.1% -> 91.0%Improved
train and test in original orientation instead of random z rotationcovering-map method · ModelNet40 classificationaccuracy (%): 91.0% -> 91.6%Improved
use covering-map representation instead of Spherical CNNSHREC17 retrieval · SHREC17 retrieval (perturbed, randomly rotated)F1@N: 0.699 -> 0.734Improved
use covering-map representation instead of SO(3) equivariant CNNsSHREC17 retrieval · SHREC17 retrieval (perturbed, randomly rotated)mAP: 0.685 -> 0.709Improved
use covering-map method instead of best retrieval entry FURUYA_DLANSHREC17 retrieval · SHREC17 retrieval (perturbed, randomly rotated)P@N: 0.814 -> 0.749Hurt
apply covering-map U-Net on 3D coordinates instead of Pointnet++human segmentation · Human body segmentationaccuracy (%): 90.77% -> 91.31%Improved
use covering-map method instead of Dynamic graph CNN on segmentationhuman segmentation · Human body segmentationaccuracy (%): 89.72% -> 91.31%Improved
use covering-map method instead of PCNN on ModelNet40ModelNet40 classification · ModelNet40 classificationaccuracy (%): 92.3% -> 91.6%Hurt

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