AI Paper Atlas

Research map / 3D vision / Face and shape

Implicit Field Supervision for Robust Non-rigid Shape Matching

Ramana Sundararaman, Gautam Pai, Maks Ovsjanikov

ECCV 2022 · 3D vision › Face and shape · approach: Optimization-based shape matching · 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 SDFNet implicit surface supervision of the latent embedding (ablation)Ours · SHREC'19mean geodesic error (cm): 11.6 -> 6.5Improved
add SDFNet implicit surface supervision of the latent embedding (ablation)Ours · FAUSTmean geodesic error (cm): 14.8 -> 2.6Improved
add off-surface field regularisations (ablation)Ours · SHREC'19mean geodesic error (cm): 7.3 -> 6.5Improved
add off-surface field regularisations (ablation)Ours · FAUSTmean geodesic error (cm): 4.9 -> 2.6Improved
add signed distance regularisation L_SDR at train and test (ablation)Ours · SHREC'19mean geodesic error (cm): 7.5 -> 6.5Improved
add signed distance regularisation L_SDR at test time (ablation)Ours · FAUSTmean geodesic error (cm): 3.6 -> 2.6Improved
add surface loss L_surf (ablation)Ours · FAUSTmean geodesic error (cm): 26.8 -> 2.6Improved
add surface loss L_surf (ablation)Ours · SHREC'19mean geodesic error (cm): 17.0 -> 6.5Improved
add Chamfer distance optimization at inference (ablation)Ours · SHREC'19mean geodesic error (cm): 10.8 -> 6.5Improved
train on more shapes (100 to 2000) from SURREAL (ablation)Ours vs 3D-CODED · SHREC'19 scenariosgeodesic errorNo clear effect
use 2k training shapes versus Oracle baselines trained on 230k with augmentationOurs · noisy and cluttered SHREC'19/FAUSTgeodesic accuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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