GEAR is an EM-style alternating optimization framework that jointly models geometry and motion in Gaussian Splatting to improve reconstruction of complex articulated objects.
Articulate-anything: Auto- matic modeling of articulated objects via a vision-language foundation model
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
FunRec reconstructs interactable 3D scenes with articulated parts from in-the-wild egocentric interaction videos, automatically discovering parts, estimating kinematics, and producing simulation-compatible meshes with large gains over prior methods.
citing papers explorer
-
GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting
GEAR is an EM-style alternating optimization framework that jointly models geometry and motion in Gaussian Splatting to improve reconstruction of complex articulated objects.
-
FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos
FunRec reconstructs interactable 3D scenes with articulated parts from in-the-wild egocentric interaction videos, automatically discovering parts, estimating kinematics, and producing simulation-compatible meshes with large gains over prior methods.