Hugging Face Daily Papers · · 3 min read

PanoWorld: Real-World Panoramic Generation

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

Project page:<a href=\"https://lihaoy-ux.github.io/panoworld-page/\" rel=\"nofollow\">https://lihaoy-ux.github.io/panoworld-page/</a><br>GitHub repo:<a href=\"https://github.com/Insta360-Research-Team/PanoWorld\" rel=\"nofollow\">https://github.com/Insta360-Research-Team/PanoWorld</a></p>\n","updatedAt":"2026-07-13T02:40:19.781Z","author":{"_id":"68e786cbfa2b7fd74a46eb23","avatarUrl":"/avatars/8292af16a47ae15b389f17adb67f3e3a.svg","fullname":"Insta360-Research","name":"Insta360-Research","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":39,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"zh","probability":0.2391471564769745},"editors":["Insta360-Research"],"editorAvatarUrls":["/avatars/8292af16a47ae15b389f17adb67f3e3a.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.09661","authors":[{"_id":"6a54429ea9d74d6e65bbcb47","name":"Haoyuan Li","hidden":false},{"_id":"6a54429ea9d74d6e65bbcb48","name":"Dizhe Zhang","hidden":false},{"_id":"6a54429ea9d74d6e65bbcb49","name":"Yuemei Zhou","hidden":false},{"_id":"6a54429ea9d74d6e65bbcb4a","name":"Xiangkai Zhang","hidden":false},{"_id":"6a54429ea9d74d6e65bbcb4b","name":"Haoran Feng","hidden":false},{"_id":"6a54429ea9d74d6e65bbcb4c","name":"Xiaofan Lin","hidden":false},{"_id":"6a54429ea9d74d6e65bbcb4d","name":"Wenjie Jiang","hidden":false},{"_id":"6a54429ea9d74d6e65bbcb4e","name":"Bo Du","hidden":false},{"_id":"6a54429ea9d74d6e65bbcb4f","name":"Ming-Hsuan Yang","hidden":false},{"_id":"6a54429ea9d74d6e65bbcb50","name":"Lu Qi","hidden":false}],"publishedAt":"2026-07-10T00:00:00.000Z","submittedOnDailyAt":"2026-07-13T00:00:00.000Z","title":"PanoWorld: Real-World Panoramic Generation","submittedOnDailyBy":{"_id":"68e786cbfa2b7fd74a46eb23","avatarUrl":"/avatars/8292af16a47ae15b389f17adb67f3e3a.svg","isPro":true,"fullname":"Insta360-Research","user":"Insta360-Research","type":"user","name":"Insta360-Research"},"summary":"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/.","upvotes":6,"discussionId":"6a54429fa9d74d6e65bbcb51","projectPage":"https://lihaoy-ux.github.io/panoworld-page/","githubRepo":"https://github.com/Insta360-Research-Team/PanoWorld","githubRepoAddedBy":"user","githubStars":2,"organization":{"_id":"644035437663594a1263c7ff","name":"Insta360","fullname":"Insta360","avatar":"https://www.gravatar.com/avatar/1af68c704803d53d59ca8a5d8a9bc3e8?d=retro&size=100"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"68e786cbfa2b7fd74a46eb23","avatarUrl":"/avatars/8292af16a47ae15b389f17adb67f3e3a.svg","isPro":true,"fullname":"Insta360-Research","user":"Insta360-Research","type":"user"},{"_id":"67ea55b90d6acd7ba31329f0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/o-lbMQKY6XJnVJNMLcKJe.png","isPro":false,"fullname":"lihaoyuan","user":"lihaoyuan-hit","type":"user"},{"_id":"6812e92b59113438668d0d76","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/YoH9F13mxXeydN7NetXLz.png","isPro":false,"fullname":"Derek Zhang","user":"derekzzzz","type":"user"},{"_id":"6405b20bbe1a9448a79a1874","avatarUrl":"/avatars/3a34ae0e8b2787ca5cfc68fcf8caf5c7.svg","isPro":false,"fullname":"Peter Hacker","user":"Gallifrey","type":"user"},{"_id":"65c4eb7cd1dcbd30d86febec","avatarUrl":"/avatars/001c8f02e8ce794b2c21883628b2da72.svg","isPro":false,"fullname":"free-bit","user":"free-bit","type":"user"},{"_id":"65fb850a63b0a74d8e48e584","avatarUrl":"/avatars/6efd5d89bc395f2627e5089b836d2ed8.svg","isPro":false,"fullname":"baoxun du","user":"fhsdhln","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"644035437663594a1263c7ff","name":"Insta360","fullname":"Insta360","avatar":"https://www.gravatar.com/avatar/1af68c704803d53d59ca8a5d8a9bc3e8?d=retro&size=100"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.09661.md","query":{}}">
Papers
arxiv:2607.09661

PanoWorld: Real-World Panoramic Generation

Published on Jul 10
· Submitted by
Insta360-Research
on Jul 13
Authors:
,

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/.

Community

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

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 paper

Datasets citing this paper

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 paper

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 paper

No Collection including this paper

Add this paper to a collection to link it from this page.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers