arxiv.orgpaperFAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
FAMOS is a feed-forward model that predicts movable-part segmentation and joint parameters for articulated 3D objects from a sparse, unordered set of partial point clouds, supporting a variable number of input views including a single one. It introduces a Multi-state Articulation Transformer with alternating state-wise and global attention plus an observed articulation span objective, and uses a procedural data generator to synthesize training assets, outperforming feed-forward and optimization-based baselines on PartNet-Mobility, ACD, and ArtiCraft-10K.
TL;DR A transformer-based feed-forward model infers 3D articulation (moving parts and joints) from sparse point-cloud observations, beating prior feed-forward and optimization baselines.
Organisations named here
- ACD
- ArtiCraft-10K
- FAMOS
- PartNet-Mobility
Techniques named here
- Multi-state Articulation Transformer
- Observed articulation span objective
- Procedural data generator
Also named here
- Transformer
Related in research