ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Sylvia, Wang, Dan, Ramamoorthi, Ravi, Cui, Xinrui
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911690488020992
author Yuan, Sylvia
Wang, Dan
Ramamoorthi, Ravi
Cui, Xinrui
author_facet Yuan, Sylvia
Wang, Dan
Ramamoorthi, Ravi
Cui, Xinrui
contents We present ArtMesh, a mesh-native method for reconstructing articulated objects explicitly as connected triangle meshes with per-part rigid motion from multi-view images in start and end states. Existing 3D Gaussian Splatting pipelines for articulated reconstruction inherit the unstructured point-based geometry of their splatting base, which provides no surface topology for reasoning about part boundaries or enforcing motion consistency along the object's connectivity. ArtMesh instead builds on a mesh-based differentiable rendering backbone, enabling part-aware dynamics to act directly on the structured topology. To make the topology compatible with articulation, we introduce part-aware restricted Delaunay remeshing, producing connected submeshes whose triangles do not cross semantic part boundaries. The dynamic mesh field then optimizes articulation using bidirectional Vertex-wise Motion Consistency on transported mesh vertices and Pixel-wise Motion Consistency on rendered RGB-D observations. We introduce Articulate-100, a new benchmark of 100 articulated objects spanning 16 PartNet-Mobility categories. On this benchmark, ArtMesh outperforms prior 3DGS-based pipelines in joint parameter estimation and part-level geometric reconstruction, with the largest gains on objects with many movable parts.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16582
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics
Yuan, Sylvia
Wang, Dan
Ramamoorthi, Ravi
Cui, Xinrui
Computer Vision and Pattern Recognition
We present ArtMesh, a mesh-native method for reconstructing articulated objects explicitly as connected triangle meshes with per-part rigid motion from multi-view images in start and end states. Existing 3D Gaussian Splatting pipelines for articulated reconstruction inherit the unstructured point-based geometry of their splatting base, which provides no surface topology for reasoning about part boundaries or enforcing motion consistency along the object's connectivity. ArtMesh instead builds on a mesh-based differentiable rendering backbone, enabling part-aware dynamics to act directly on the structured topology. To make the topology compatible with articulation, we introduce part-aware restricted Delaunay remeshing, producing connected submeshes whose triangles do not cross semantic part boundaries. The dynamic mesh field then optimizes articulation using bidirectional Vertex-wise Motion Consistency on transported mesh vertices and Pixel-wise Motion Consistency on rendered RGB-D observations. We introduce Articulate-100, a new benchmark of 100 articulated objects spanning 16 PartNet-Mobility categories. On this benchmark, ArtMesh outperforms prior 3DGS-based pipelines in joint parameter estimation and part-level geometric reconstruction, with the largest gains on objects with many movable parts.
title ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.16582