FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations

Hugging Face Daily Papers Papers
3d-modeling articulation sparse-observations feed-forward transformer point-cloud computer-vision

Summary

FAMOS is a feed-forward model that predicts movable-part segmentation and joint parameters from sparse point clouds using a Multi-state Articulation Transformer and a procedural data generator, showing consistent improvements over baselines in experiments.

Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer articulation from a single observation and therefore rely heavily on learned category-level shape priors. We present FAMOS, a feed-forward model that predicts movable-part segmentation and joint parameters from a sparse, unordered set of partial point clouds. Our model jointly reasons over multiple observations and naturally supports a variable number of inputs, including a single view. To aggregate articulation cues across observations, we introduce a Multi-state Articulation Transformer with alternating state-wise and global attention. We further propose an observed articulation span objective that supervises the motion range each part exhibits across the input observations, encouraging the model to leverage the full observation set. To overcome the limited scale and diversity of existing datasets, we introduce a procedural data generator that synthesizes self-annotated assets during training. Experiments on PartNet-Mobility, ACD, and ArtiCraft-10K demonstrate consistent improvements over both feed-forward and optimization-based baselines. Project page: https://kevinqu7.github.io/famos
Original Article
View Cached Full Text

Cached at: 09/18/26, 11:01 AM

Paper page - FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations

Source: https://huggingface.co/papers/2609.20817

Abstract

Modelingarticulatedobjectsfromsparsemonocularviewsischallengingbecauseeachobservationrevealsonlypartialgeometryandmotionevidence.Mostfeed-forwardmethodsinferarticulationfromasingleobservationandthereforerelyheavilyonlearnedcategory-levelshapepriors.WepresentFAMOS,afeed-forwardmodelthatpredictsmovable-partsegmentationandjointparametersfromasparse,unorderedsetofpartialpointclouds.Ourmodeljointlyreasonsovermultipleobservationsandnaturallysupportsavariablenumberofinputs,includingasingleview.Toaggregatearticulationcuesacrossobservations,weintroduceaMulti-stateArticulationTransformerwithalternatingstate-wiseandglobalattention.Wefurtherproposeanobservedarticulationspanobjectivethatsupervisesthemotionrangeeachpartexhibitsacrosstheinputobservations,encouragingthemodeltoleveragethefullobservationset.Toovercomethelimitedscaleanddiversityofexistingdatasets,weintroduceaproceduraldatageneratorthatsynthesizesself-annotatedassetsduringtraining.ExperimentsonPartNet-Mobility,ACD,andArtiCraft-10Kdemonstrateconsistentimprovementsoverbothfeed-forwardandoptimization-basedbaselines.Projectpage:https://kevinqu7.github.io/famos

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2609\.20817

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.20817 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.20817 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.20817 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Articulated Object Reconstruction from Rest-State Observation

Hugging Face Daily Papers

This paper introduces a rest-state framework that reconstructs articulated objects from a single closed configuration, using explicit meshes, vision-language outputs, and video diffusion models to generate and validate articulation hypotheses without observed motion.

AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

Hugging Face Daily Papers

This paper introduces AnyMo, a unified multimodal framework for human motion generation that combines a Residual FSQ-based motion tokenizer with a scalable masked modeling transformer, along with the OmniHuMo dataset of over 5,000 hours of motion data to enable high-quality synthesis under arbitrary modality combinations.

Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction

Hugging Face Daily Papers

Lite3R is a model-agnostic framework that improves the efficiency of transformer-based 3D reconstruction using sparse linear attention and FP8-aware quantization. It reduces latency and memory usage by up to 2.4x while maintaining geometric accuracy on backbones like VGGT and DA3-Large.

AFUN: Towards an Affordance Foundation Model for Functionality Understanding

Hugging Face Daily Papers

AFUN proposes an affordance foundation model that predicts functional masks and 3D motion curves from RGB-D observations and language descriptions, enabling generalizable robot manipulation across diverse environments. The model outperforms baselines on multiple benchmarks and can be deployed for real-world tasks without fine-tuning.