GEAR is an EM-style alternating optimization framework that jointly models geometry and motion in Gaussian Splatting to improve reconstruction of complex articulated objects.
Structure from action: Learning interactions for articulated object 3d structure discovery
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
A pipeline that reconstructs articulated objects from sparse unposed images by aligning independent per-pose reconstructions via learned deformation fields and progressive static/moving part disentanglement.
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.
-
PAOLI: Pose-free Articulated Object Learning from Sparse-view Images
A pipeline that reconstructs articulated objects from sparse unposed images by aligning independent per-pose reconstructions via learned deformation fields and progressive static/moving part disentanglement.