Related papers: PanoWorld: Real-World Panoramic Generation

PanoWorld: Real-World Panoramic Generation

URL: http://arxiv.org/abs/2607.09661v1
Date: Fri, 10 Jul 2026 17:59:32 GMT
Title: PanoWorld: Real-World Panoramic Generation
Abstract summary: We propose PanoWorld, which simplifies camera trajectories into translations via fixed headings for both current-action modeling and long-range memory.<n>Extensive experiments on World360 demonstrate the effectiveness of PanoWorld, outperforming alternative methods by a large margin.
Score: 68.3569360188378
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
Abstract: 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/.

Related papers

Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction [32.80582033500264]
PanoLOG is a two-stage coarse-to-fine framework equipped with a Geometry and Gradient-based Partitioning Strategy.<n>We construct Pano360, the first benchmark on large-scale panoramic dataset for outdoor scene reconstruction.
arXiv Detail & Related papers (2026-07-09T17:59:43Z)
PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis [9.056861577664717]
PanoWorld is a generative spatial world model that treats whole-house synthesis as autoregressive generation of node-based panoramas.<n>It preserves high-frequency 2D synthesis quality while improving cross-node layout and material consistency.
arXiv Detail & Related papers (2026-05-18T06:25:37Z)
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World [20.19893789145407]
We study pano-native understanding, which requires an MLLM to reason over an equirectangular projection panorama as a continuous, observer-centered space.<n>We introduce PanoWorld with Spherical Spatial Cross-Attention, which injects spherical geometry into the visual stream.<n>Experiments show that PanoWorld substantially outperforms both proprietary and open-source baselines on PanoSpace-Bench, H* Bench, and R2R-CE Val-Unseen benchmarks.
arXiv Detail & Related papers (2026-05-13T08:31:22Z)
Map2World: Segment Map Conditioned Text to 3D World Generation [64.2098235580955]
3D world generation is essential for immersive content creation or autonomous driving simulation.<n>Recent advances in 3D world generation have shown promising results; however, these methods are constrained by grid layouts.<n>We introduce a novel framework, Map2World, that first enables 3D world generation conditioned on user-defined segment maps of arbitrary shapes and scales.
arXiv Detail & Related papers (2026-05-01T16:56:49Z)
Pano360: Perspective to Panoramic Vision with Geometric Consistency [7.713672589538202]
We adopt a novel transformer-based architecture to achieve 3D awareness and aggregate global information across all views.<n>To establish an evaluation benchmark and train our network, we constructed a large-scale dataset of real-world scenes.
arXiv Detail & Related papers (2026-03-12T14:56:14Z)
Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation [68.95366581365829]
We present a panoramic metric depth foundation model that generalizes across diverse scene distances.<n>We collect a large-scale dataset by combining public datasets, high-quality synthetic data from our UE5 simulator and text-to-image models, and real panoramic images from the web.
arXiv Detail & Related papers (2025-12-18T18:59:29Z)
DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training [76.82789568988557]
DiT360 is a DiT-based framework that performs hybrid training on perspective and panoramic data for panoramic image generation.<n>Our method achieves better boundary consistency and image fidelity across eleven quantitative metrics.
arXiv Detail & Related papers (2025-10-13T17:59:15Z)
PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion [87.13016347332943]
PanoWorld-X is a novel framework for high-fidelity and controllable panoramic video generation with diverse camera trajectories.<n>Our experiments demonstrate superior performance in various aspects, including motion range, control precision, and visual quality.
arXiv Detail & Related papers (2025-09-29T16:22:00Z)
ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models [52.87334248847314]
We propose a novel framework utilizing pretrained perspective video models for generating panoramic videos.<n>Specifically, we design a novel panorama representation named ViewPoint map, which possesses global spatial continuity and fine-grained visual details simultaneously.<n>Our method can synthesize highly dynamic and spatially consistent panoramic videos, achieving state-of-the-art performance and surpassing previous methods.
arXiv Detail & Related papers (2025-06-30T04:33:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.