PanoWorld: Real-World Panoramic Generation

Hugging Face Daily Papers Papers
panoramic-generation world-models rotation-equivariant omnidirectional dataset computer-vision generative-models

Summary

PanoWorld proposes a method for long-range memory in panoramic world models using rotation-equivariant representations, with a three-stage training pipeline and a new large-scale dataset World360. The model outperforms alternatives by a large margin.

In this work, we aim to address the challenge of long-range memory in panoramic world models by exploiting the rotation-equivariant property of omnidirectional representations, where rotation can be treated as an implicit geometric transformation.Building on this insight, we propose PanoWorld, which simplifies camera trajectories into translations via fixed headings for both current-action modeling and long-range memory through Dense Panoramic Ray-Conditioning (DPRC) and Geometry-aware Memory Augmentation (GMA).Then, a three-stage training pipeline is introduced to progressively optimize each component. To better evaluate physical consistency under large-scale spatial variations and diverse illumination conditions, where existing datasets are relatively stable, we construct World360, a large-scale dataset consisting of both real-world video clips collected via panoramic unmanned aerial vehicles and high-quality simulated clips generated by AirSim360.Extensive experiments on World360 demonstrate the effectiveness of PanoWorld, outperforming alternative methods by a large margin.Our models, training code, and dataset will be publicly available. More information can be found on our project page: https://lihaoy-ux.github.io/panoworld-page/.
Original Article
View Cached Full Text

Cached at: 07/13/26, 07:50 AM

Paper page - PanoWorld: Real-World Panoramic Generation

Source: https://huggingface.co/papers/2607.09661

Abstract

Inthiswork,weaimtoaddressthechallengeoflong-rangememoryinpanoramicworldmodelsbyexploitingtherotation-equivariantpropertyofomnidirectionalrepresentations,whererotationcanbetreatedasanimplicitgeometrictransformation.Buildingonthisinsight,weproposePanoWorld,whichsimplifiescameratrajectoriesintotranslationsviafixedheadingsforbothcurrent-actionmodelingandlong-rangememorythroughDensePanoramicRay-Conditioning(DPRC)andGeometry-awareMemoryAugmentation(GMA).Then,athree-stagetrainingpipelineisintroducedtoprogressivelyoptimizeeachcomponent.Tobetterevaluatephysicalconsistencyunderlarge-scalespatialvariationsanddiverseilluminationconditions,whereexistingdatasetsarerelativelystable,weconstructWorld360,alarge-scaledatasetconsistingofbothreal-worldvideoclipscollectedviapanoramicunmannedaerialvehiclesandhigh-qualitysimulatedclipsgeneratedbyAirSim360.ExtensiveexperimentsonWorld360demonstratetheeffectivenessofPanoWorld,outperformingalternativemethodsbyalargemargin.Ourmodels,trainingcode,anddatasetwillbepubliclyavailable.Moreinformationcanbefoundonourprojectpage:https://lihaoy-ux.github.io/panoworld-page/.

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2607\.09661

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

Models citing this paper1

#### Insta360-Research/PanoWorld Updatedabout 6 hours ago • 1

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.09661 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.09661 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

PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World

Hugging Face Daily Papers

PanoWorld introduces spherical spatial cross-attention for panoramic reasoning, addressing limitations of MLLMs in 360-degree spatial understanding. It builds a large-scale pipeline for geometry-aware supervision and proposes a diagnostic benchmark, achieving state-of-the-art results on multiple benchmarks.

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

Hugging Face Daily Papers

PaGeR adapts the multi-view perspective foundation model Depth Anything 3 to predict scale-invariant and metric depth, surface normals, and sky segmentation from a single equirectangular image, using a fixed cubemap representation that keeps VRAM and runtime constant. The paper also releases the ZüriPano and PanoInfinigen datasets.