AI Paper Atlas

Research map / 3D vision / Face and shape

Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence

Ronghan Chen, Yang Cong, Jiahua Dong

ICCV 2021 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 6 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-Intrinsic Autoencoder instead of global embedding (ablation)UD2E-Net · SURREAL (230k)C_De (cm): 2.23 -> 1.91Improved
add Extrinsic-Intrinsic Autoencoder instead of global embedding (ablation)UD2E-Net · SURREAL (23k)C_De (cm): 2.61 -> 2.04Improved
add bounded MMD loss (ablation)UD2E-Net · SURREAL (230k)C_De (cm): 2.47 -> 1.91Improved
add bounded MMD loss (ablation)UD2E-Net · SURREAL (23k)C_De (cm): 2.47 -> 2.04Improved
add trace and propagation instead of knn node assignment (ablation)UD2E-Net · SURREAL (230k)C_De (cm): 2.85 -> 1.91Improved
add trace and propagation instead of knn node assignment (ablation)UD2E-Net · SURREAL (23k)C_De (cm): 3.08 -> 2.04Improved
use 10D canonical shape instead of 3D (ablation)UD2E-Net · SURREAL (230k)C_De (cm): 2.02 -> 1.91Improved
set bounded MMD weight beta to 0.01 instead of 0 (ablation)UD2E-Net · SURREAL (230k)C_De (cm): 2.30 -> 1.91Improved
retrieve a similar template instead of a fixed oneUD2E-Net · SURREAL (23k)R_Gt (cm): 1.78 -> 1.12Improved
retrieve a similar template instead of a fixed oneUD2E-Net · DFAUSTR_Gt (cm): 1.84 -> 1.752Improved
reduce SURREAL training data from 230k to 23k3D-CODED and Elementary · SURREALreconstruction errorHurt
reduce SURREAL training data from 230k to 23kUD2E-Net · SURREALreconstruction errorNo clear effect

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