TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable Manipulation

Hugging Face Daily Papers Papers
tabletop-dataset robotic-manipulation real2sim scene-reconstruction large-scale generalizable-manipulation

Summary

TableVerse introduces a fully automated Real2Sim pipeline that converts unstructured, in-the-wild images into high-fidelity, simulation-ready tabletop environments with accurate metrics and physical stability, along with a large-scale dataset (TableVerse-100K) for generalizable robotic manipulation.

The development of generalizable robotic manipulation policies is inherently bounded by the availability of large-scale, high-fidelity scene data. While recent automated synthesis methods attempt to bridge this gap via text-to-layout hallucination or simplified procedural generation, they frequently suffer from physical implausibility and fail to capture the complex, dense clutter of actual human environments. In this paper, we introduce TableVerse, a fully automated Real2Sim pipeline that shifts the paradigm from imaginative layout generation to deterministic reconstruction from unstructured, in-the-wild image data. Our framework seamlessly processes unscripted internet media into high-fidelity, simulation-ready tabletop environments with accurate metric scales, authentic topologies, and verified mechanical stability. Furthermore, an automated task-conditioned trajectory generation framework is integrated to synthesize high-quality, collision-free pick-and-place demonstrations. Leveraging this complete pipeline, we construct the TableVerse-100K Dataset, a large-scale corpus comprising 100,000 unique, physically consistent environments paired with interactive manipulation trajectories. By capturing diverse asset compositions, realistic spatial distributions, and high-quality demonstrations, TableVerse-100K establishes a highly scalable and high-fidelity data foundation, providing significant value to facilitate future research in generalizable robotic manipulation tasks.
Original Article
View Cached Full Text

Cached at: 07/24/26, 05:06 AM

Paper page - TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable Manipulation

Source: https://huggingface.co/papers/2607.21017

Abstract

Thedevelopmentofgeneralizableroboticmanipulationpoliciesisinherentlyboundedbytheavailabilityoflarge-scale,high-fidelityscenedata.Whilerecentautomatedsynthesismethodsattempttobridgethisgapviatext-to-layouthallucinationorsimplifiedproceduralgeneration,theyfrequentlysufferfromphysicalimplausibilityandfailtocapturethecomplex,denseclutterofactualhumanenvironments.Inthispaper,weintroduceTableVerse,afullyautomatedReal2Simpipelinethatshiftstheparadigmfromimaginativelayoutgenerationtodeterministicreconstructionfromunstructured,in-the-wildimagedata.Ourframeworkseamlesslyprocessesunscriptedinternetmediaintohigh-fidelity,simulation-readytabletopenvironmentswithaccuratemetricscales,authentictopologies,andverifiedmechanicalstability.Furthermore,anautomatedtask-conditionedtrajectorygenerationframeworkisintegratedtosynthesizehigh-quality,collision-freepick-and-placedemonstrations.Leveragingthiscompletepipeline,weconstructtheTableVerse-100KDataset,alarge-scalecorpuscomprising100,000unique,physicallyconsistentenvironmentspairedwithinteractivemanipulationtrajectories.Bycapturingdiverseassetcompositions,realisticspatialdistributions,andhigh-qualitydemonstrations,TableVerse-100Kestablishesahighlyscalableandhigh-fidelitydatafoundation,providingsignificantvaluetofacilitatefutureresearchingeneralizableroboticmanipulationtasks.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2607\.21017

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/2607.21017 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.21017 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.21017 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

Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator

Hugging Face Daily Papers

Image2Sim is a neural simulation framework that creates high-fidelity interactive environments from RGB-D images, enabling scalable training for embodied navigation agents. It generates nearly 20K scenes and over 10 million training samples, showing strong benchmark improvements and effective real-world zero-shot transfer.