FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
FAMOS uses several sparse partial views at once to estimate moving parts and joints, instead of leaning on one-view category priors.
The paper says the model takes an unordered set of partial point clouds and predicts movable-part segmentation plus joint parameters. Its Multi-state Articulation Transformer alternates state-wise and global attention to combine cues across observations. The authors also add an objective for the observed motion span and a procedural generator for self-annotated training assets. They report consistent gains over feed-forward and optimization-based baselines on PartNet-Mobility, ACD, and ArtiCraft-10K. HF Daily Papers' note
The paper says the model takes an unordered set of partial point clouds and predicts movable-part segmentation plus joint parameters. Its Multi-state Articulation Transformer alternates state-wise and global attention to combine cues across observations. The authors also add an objective for the observed motion span and a procedural generator for self-annotated training assets. They report consistent gains over feed-forward and optimization-based baselines on PartNet-Mobility, ACD, and ArtiCraft-10K. HF Daily Papers' note
score 4