AI Paper Atlas

Research map / Point clouds / Shape and surface completion

DDM: A Metric for Comparing 3D Shapes Using Directional Distance Fields

Siyu Ren, Junhui Hou, Xiaodong Chen, Hongkai Xiong, Wenping Wang

TPAMI 2025 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 15 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
use DDM instead of CDtemplate surface fitting · 3DCaricShopF-0.005: 0.9560 -> 0.9833Improved
use DDM instead of CD as unsupervised lossNSFP scene flow · FlyingThings3DEPE3D (m): 0.0899 -> 0.0657Improved
use DDM instead of CD as unsupervised lossSCOOP scene flow · FlyingThings3DEPE3D (m): 0.0839 -> 0.0732Improved
use DDM instead of CD in optimization-based scene flowoptimization scene flow · FlyingThings3DEPE3D (m): 0.1557 -> 0.0843Improved
refine MAC with DDMMAC rigid registration · 3DMatch (clean)SR (%): 82.58 -> 82.77Improved
refine MAC with DDM on outlier dataMAC rigid registration · 3DMatch (50% outliers)SR (%): 80.50 -> 78.22Hurt
add confidence score beta (beta=20 instead of 0) (ablation)DDM rigid registration · 3DMatch rigidSR (%): 37.11 -> 82.77Improved
increase beta from 20 to 30 (ablation)DDM rigid registration · 3DMatch rigidSR (%): 82.77 -> 81.78Hurt
increase reference points M from 1x to 20x (ablation)DDM rigid registration · 3DMatch rigidSR (%): 83.20 -> 82.65No clear effect
increase reference points M from 2e4 to 4e4 (ablation)DDM non-rigid registration · human motion sequencesRMSE (x1e-2): 0.857 -> 0.612Improved
increase reference points M from 4e4 to 6e4 (ablation)DDM non-rigid registration · human motion sequencesRMSE (x1e-2): 0.612 -> 0.580Improved
increase sigma from 0.05 to 0.1 (ablation)DDM non-rigid registration · human motion sequencesRMSE (x1e-2): 0.646 -> 0.612Improved

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