AI Paper Atlas

Research map / 3D vision / Face and shape

3D-CODED: 3D Correspondences by Deep Deformation

Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry

ECCV 2018 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 314 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 the latent-feature reconstruction optimization (regression) step (ablation)3D-CODED · FAUST-intererror (cm): 6.29 -> 3.255Improved
add regular point sampling on training surfaces (ablation)3D-CODED with regression · FAUST-intererror (cm): 3.255 -> 3.048Improved
add high-resolution template for the nearest-neighbor step (ablation)3D-CODED · FAUST-intererror (cm): 3.048 -> 2.878Improved
train on augmented synthetic data instead of FAUST training set (ablation)3D-CODED · FAUST-intererror (cm): 18.22 -> 3.26Improved
augment synthetic dataset over the non-augmented one (ablation)3D-CODED · FAUST-intererror (cm): 5.63 -> 3.26Improved
increase augmented training shapes from 1e3 to 2.3e5 (ablation)3D-CODED · FAUST-intererror (cm): 5.76 -> 3.26Improved
add correspondence supervision over regularized unsupervised training (ablation)3D-CODED · FAUST-intererror (cm): 4.835 -> 2.878Improved
add surface regularization to the Chamfer-only unsupervised loss (ablation)3D-CODED · FAUST-intererror (cm): 8.727 -> 4.835Improved
use FAUST template instead of zero or separated template (ablation)3D-CODED · FAUST-intererror (cm): 3.385 -> 3.255 (zero), 3.314 -> 3.255 (separated)Improved
use symmetric Chamfer distance instead of asymmetric (ablation)3D-CODED · FAUST-intererror (cm): 4.023 -> 3.255, 3.336 -> 3.255Improved
use rotation-invariant network instead of orientation search (ablation)3D-CODED · FAUST-intererror (cm): 2.878 -> 3.10Hurt
increase TOSCA sampling perturbation to strongest level3D-CODED · TOSCA horseerror (cm): 4.82 -> 9.93Hurt

Later papers that compared with this method

15 later accepted papers report 3DCODED as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.

7 more not listed.

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