CVPR Findings2026
GEAR: GEometry-Motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting
Jialin Li, Bin Fu, Ruiping Wang, Xilin Chen
Abstract
High-fidelity interactive digital assets are essential for embodied intelligence and robotic interaction, yet articulated objects remain challenging to reconstruct due to their complex structures and coupled geometry-motion relationships. Existing methods suffer from instability in geometry-motion joint optimization, while their generalization remains limited on complex multi-joint or out-of-distribution objects. To address these challenges, we propose GEAR, an EM-style alternating optimization framework that jointly models geometry and motion as interdependent components within a Gaussian Splatting representation. GEAR treats part segmentation as a latent variable and joint motion parameters as explicit variables, alternately refining them for improved convergence and geometric-motion consistency. To enhance part segmentation quality without sacrificing generalization, we leverage a vanilla 2D segmentation model to provide multi-view part priors, and employ a weakly supervised constraint to regularize the latent variable. Experiments on multiple benchmarks and our newly constructed dataset GEAR-Multi demonstrate that GEAR achieves state-of-the-art results in geometric reconstruction and motion parameters estimation, particularly on complex articulated objects with multiple movable parts.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction cites UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction
- 2D Gaussian Splatting for Geometrically Accurate Radiance Fields cites UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction
- 2D Gaussian Splatting for Geometrically Accurate Radiance Fields cites NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
Builds on34
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt et al.NeurIPS 2021 · 2,500 citations
- UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View ReconstructionMichael Oechsle, Songyou Peng, Andreas GeigerICCV 2021 · 885 citations
- 2D Gaussian Splatting for Geometrically Accurate Radiance FieldsBinbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger et al.SIGGRAPH 2024 · 660 citations
Related papers
- SPLART: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian SplattingShengjie Lin, Jiading Fang, Muhammad Zubair Irshad, Vitor Campagnolo Guizilini et al.ICCV 2025 · 2 citations
- ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility ProposalsXuelu Li, Zhaonan Wang, Xiaogang Wang, Lei Wu et al.CVPR 2026 · 1 citation
- REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian SplattingDi Wu, Liu Liu, Anran Huang, 玉研 刘 et al.CVPR 2026 · 6 citations
- ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian SplattingJunfu Guo, Yu Xin, Gaoyi Liu, Kai Xu et al.CVPR 2025
- Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static DisentanglementHao Ai, Wenjie Chang, Jianbo Jiao, Ales Leonardis et al.ICLR 2026 · 7 citations
