AI Paper Atlas

Research map / 3D vision / Face and shape

Spatially and Spectrally Consistent Deep Functional Maps

Mingze Sun, Shiwei Mao, Puhua Jiang, Maks Ovsjanikov, Ruqi Huang

ICCV 2023 · 3D vision › Face and shape · approach: Optimization-based shape matching · 33 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 spatial branch (point-wise map from spectral latent shape) to a standard deep functional map (ablation)Deep Functional Maps · SMAL_rmean geodesic error (x100): 33.4 -> 5.4Improved
add spectral branch (FMreg layer) to spatial-only variant (ablation)Deep Functional Maps · SMAL_rmean geodesic error (x100): 14.3 -> 5.4Improved
use curriculum updating scheme for alpha instead of fixed alpha = 50 (ablation)two-branch DFM · SMAL_rmean geodesic error (x100): 35.2 -> 5.4Improved
use curriculum updating scheme for alpha instead of fixed alpha = 1 (ablation)two-branch DFM · SMAL_rmean geodesic error (x100): 6.6 -> 5.4Improved
add two-branch design to SURFMNet (ablation)SURFMNet · FAUST_r / SCAPE_r / SMAL_r / DT4D-Hmean geodesic error (x100): 6.0 -> 3.5 (FAUST_r); 18.3 -> 15.0 (DT4D-H)Improved
increase functional map dimension to 80 (ablation)two-branch DFM · Train FAUST_r, test SHREC19_rmean geodesic error (x100): 3.8 -> 5.5 (generalization); 2.3 -> 1.7 (FAUST_r)Mixed
down-sample vertices to 3000 and descriptors to 30 dims (ablation)two-branch DFM · SMAL_rmean geodesic error (x100): 5.4 -> 5.7 / 5.9No clear effect
two-branch spectral and spatial consistency vs best prior on non-isometric DT4D-Htwo-branch DFM · DT4D-H (168 train)mean geodesic error (x100): 22.4 -> 7.7Improved
two-branch DFM in standard FAUST_r test vs UDMSMtwo-branch DFM · Train FAUST_r, test FAUST_rmean geodesic error (x100): 1.5 (UDMSM) vs 2.3Hurt

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