paper-with-me

홈 › Papers

GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting

2026-04-09 · Jialin Li, Bin Fu, Ruiping Wang, Xilin Chen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.07728

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DYNAMO: Dependency-Aware Deep Learning Framework for Articulated Assembly Motion Prediction

2025-09-15 · Mayank Patel, Rahul Jain, Asim Unmesh, Karthik Ramani arxiv

Understanding the motion of articulated mechanical assemblies from static geometry remains a core challenge in 3D perception and design automation. Prior work on everyday articulated objects such as doors and laptops typ…

Point Clouds

Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data

2019-05-12 · Onorina Kovalenko, Vladislav Golyanik, Jameel Malik, Ahmed Elhayek 외

Recovery of articulated 3D structure from 2D observations is a challenging computer vision problem with many applications. Current learning-based approaches achieve state-of-the-art accuracy on public benchmarks but are …

3D Reconstruction

GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objects

2025-08-20 · Licheng Shen, Saining Zhang, Honghan Li, Peilin Yang 외 arxiv

Reconstructing articulated objects is essential for building digital twins of interactive environments. However, prior methods typically decouple geometry and motion by first reconstructing object shape in distinct state…

LA-Sign: Looped Transformers with Geometry-aware Alignment for Skeleton-based Sign Language Recognition

2026-03-30 · Muxin Pu, Mei Kuan Lim, Chun Yong Chong, Chen Change Loy arxiv

Skeleton-based isolated sign language recognition (ISLR) demands fine-grained understanding of articulated motion across multiple spatial scales, from subtle finger movements to global body dynamics. Existing approaches …

Sign Language RecognitionRepresentation Learning

Survey on Modeling of Human-made Articulated Objects

2024-03-22 · Jiayi Liu, Manolis Savva, Ali Mahdavi-Amiri

3D modeling of articulated objects is a research problem within computer vision, graphics, and robotics. Its objective is to understand the shape and motion of the articulated components, represent the geometry and mobil…

ObjectSurvey