AI Paper Atlas

Research map / 3D vision / Gaussian splatting

StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction

GaHye Lee, Gyoonseo Kim, Wonjong Jang, Jooeun Son, Seungyong Lee

ECCV 2026 · 3D vision › Gaussian splatting · approach: Animatable Gaussian human avatars · 0 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 structure-aware OBB losses (part fitting and contact) over photometric-only optimization (ablation)StructureGS · PARISangular and Chamfer errorImproved
add extent regularization L_ext (ablation)StructureGS · PARISCD-mImproved
use structure-aware method instead of ArticulatedGS under 10 viewsStructureGS · PARIS sparse views (10)angular error (deg): 8.553 -> 0.701Improved
use structure-aware method instead of ArticulatedGS under 100 viewsStructureGS · PARIS full views (100)angular error (deg): 0.091 -> 0.088Improved
use structure-aware method instead of ArticulatedGSStructureGS · PARIS sparse views (10)PSNR: 23.320 -> 33.264Improved
use structure-aware method instead of ArticulatedGSStructureGS · PARIS full views (100)PSNR: 37.336 -> 43.39Improved
use structure-aware method instead of ScrewSplatStructureGS · DTA StorageCD-w (x1000): 38.15 -> 3.238Improved
use structure-aware method instead of ScrewSplat on Storage part 0 angular errorStructureGS · DTA Storageangular error part 0 (deg): 0.052 -> 2.165Hurt
use structure-aware method instead of ScrewSplatStructureGS · ArtGS-Multi (4-7 parts)angular error (deg): 27.4 -> 3.67Improved
reduce training views from 100 to 10 (ablation)ArticulatedGS · PARISangular error and Chamfer distanceHurt
reduce training views from 100 to 10 (ablation)StructureGS · PARISangular error (deg): 0.088 -> 0.701Hurt
perturb OBB initialization (clustering noise, point-cloud noise, Pi3 instead of VGGT) (ablation)StructureGS · PARIS sparse views (10)OBB fitting 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