AI Paper Atlas

Research map / Point clouds / Shape and surface completion

LiteGE: Lightweight Geodesic Embedding for Efficient Geodesics Computation and Non-Isometric Shape Correspondence

Yohanes Yudhi Adikusuma, Qixing Huang, Ying He

AAAI 2026 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 2 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 LiteGE instead of NeuroGF on 300-point sparse cloudsgeodesic regression · SMAL, 300 pointsmean L1 error: 75 -> 3.4Improved
use LiteGE instead of NeuroGF on 2000-point cloudsgeodesic regression · SMAL, 2000 pointsmean L1 error: 13 -> 2.3Improved
use LiteGE instead of NeuroGF for batch queriesgeodesic regression · 2K point clouds, N_Q=64memory (MB): 10344 -> 34.5Improved
use LiteGE instead of NeuroGF for batch queriesgeodesic regression · 2K point clouds, N_Q=64inference time (ms): 1529 -> 13.4Improved
use LiteGE instead of NeuroGF on single querygeodesic regression · 2K point clouds, N_Q=1inference time (ms): 88 -> 1.9Improved
add 0.01-scale Gaussian noise to input point cloudsLiteGE · SMAL, 2K pointsmean L1 error: 4.3No clear effect
use LiteGE instead of SMS on broken meshesshape correspondence · Broken Mesh 5Kgeodesic error: 28 -> 8Improved
use LiteGE instead of SMS on broken meshesshape correspondence · Broken Mesh 5KAUC: 33.2 -> 69.5Improved
use LiteGE instead of SMS on clean template meshesshape correspondence · Template 4Kgeodesic error: 2.2 -> 2.5Hurt
use LiteGE instead of SMS on remeshed 5K modelsshape correspondence · Remeshed 5Kgeodesic error: 7.44 -> 7.2Improved
use LiteGE instead of SMS on anisotropic 10K modelsshape correspondence · Anisotropic 10Kgeodesic error: 6.8 -> 7Hurt
increase point-cloud samples from 800 to 15,000 (ablation)LiteGE path tracing · SMAL, 8 shapesmedian prediction error: 4.73 -> 3.66Improved

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