AI Paper Atlas

Research map / 3D vision / Face and shape

OperatorNet: Recovering 3D Shapes From Difference Operators

Ruqi Huang, Marie-Julie Rakotosaona, Panos Achlioptas, Leonidas J. Guibas, Maks Ovsjanikov

ICCV 2019 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 19 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 extrinsic shape difference to intrinsic shape differences (ablation)OperatorNet · DFAUST testd_R (x1e-4): 2.41 -> 1.11Improved
add intrinsic shape differences to extrinsic shape difference (ablation)OperatorNet · DFAUST testd_R (x1e-4): 1.25 -> 1.11Improved
use ground-truth correspondences instead of computed functional maps (Int+Ext) (ablation)OperatorNet · DFAUST testd_R (x1e-4): 6.22 -> 1.11Improved
use ground-truth correspondences instead of computed functional maps (Ext) (ablation)OperatorNet · DFAUST testd_R (x1e-4): 3.86 -> 1.25Improved
replace SfL baseline with OperatorNet (Int+Ext)OperatorNet · DFAUST testd_R (x1e-4): 48.8 -> 1.11Improved
replace nearest neighbor retrieval with OperatorNet (Int+Ext)OperatorNet · DFAUST testd_V: 0.005 -> 0.014Hurt
replace SfL (full Laplacian input) with OperatorNet (Int+Ext)OperatorNet · DFAUST testd_E: 0.012 -> 0.045Hurt
add area and conformal differences to extrinsic (all three vs Area only) (ablation)OperatorNet, Conv. 8 · DFAUST testreconstruction loss (x1e-4): 8.61 -> 2.46Improved
add area difference to E+C (ablation)OperatorNet, Conv. 8 · DFAUST testreconstruction loss (x1e-4): 2.56 -> 2.46Improved
use a shallower single-layer conv encoder (Conv. 8) instead of four layers (ablation)OperatorNet, A+E+C · DFAUST testreconstruction loss (x1e-4): 4.24 -> 2.46Improved
use a single-layer encoder instead of two layers (ablation)OperatorNet, A+E+C · DFAUST testreconstruction loss (x1e-4): 3.05 -> 2.46Improved
use multiplicative (Lie algebra) interpolation instead of linear interpolation of shape differences (ablation)OperatorNet · shape interpolationsmoothness of consecutive reconstructionsImproved

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