https://yukun-huang.github.io/DreamCube/

\n","updatedAt":"2025-06-23T03:11:47.586Z","author":{"_id":"638ee900ee7e45e0474a5712","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg","fullname":"Yukun Huang","name":"KevinHuang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":7}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.11782249808311462},"editors":["KevinHuang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg"],"reactions":[],"isReport":false},"replies":[{"id":"6858ce565ecded3f80393383","author":{"_id":"63612d47c12a09b8a3135aa4","avatarUrl":"/avatars/737aa4c8394066bf415ddf20d1e35cc0.svg","fullname":"Spergware","name":"sneedingface","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1},"createdAt":"2025-06-23T03:47:34.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Is there a demo somewhere to try?","html":"

Is there a demo somewhere to try?

\n","updatedAt":"2025-06-23T03:47:34.566Z","author":{"_id":"63612d47c12a09b8a3135aa4","avatarUrl":"/avatars/737aa4c8394066bf415ddf20d1e35cc0.svg","fullname":"Spergware","name":"sneedingface","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9601845741271973},"editors":["sneedingface"],"editorAvatarUrls":["/avatars/737aa4c8394066bf415ddf20d1e35cc0.svg"],"reactions":[],"isReport":false,"parentCommentId":"6858c5f3b8646f42a8bf2bf1"}},{"id":"6858d6c436ce8a8abb7b18e5","author":{"_id":"638ee900ee7e45e0474a5712","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg","fullname":"Yukun Huang","name":"KevinHuang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":7},"createdAt":"2025-06-23T04:23:32.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Hi! We provide a gradio demo in [github repo](https://github.com/yukun-huang/DreamCube). We are looking for GPU support for building an online demo: https://huggingface.co/spaces/huggingface/InferenceSupport/discussions/2602","html":"

Hi! We provide a gradio demo in github repo. We are looking for GPU support for building an online demo: https://huggingface.co/spaces/huggingface/InferenceSupport/discussions/2602

\n","updatedAt":"2025-06-23T04:23:32.351Z","author":{"_id":"638ee900ee7e45e0474a5712","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg","fullname":"Yukun Huang","name":"KevinHuang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":7}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.750654935836792},"editors":["KevinHuang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg"],"reactions":[],"isReport":false,"parentCommentId":"6858c5f3b8646f42a8bf2bf1"}}]},{"id":"6858d7e11d935f76ad0999b8","author":{"_id":"638ee900ee7e45e0474a5712","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg","fullname":"Yukun Huang","name":"KevinHuang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":7},"createdAt":"2025-06-23T04:28:17.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Looking for GPU support for building an online demo: https://huggingface.co/spaces/huggingface/InferenceSupport/discussions/2602","html":"

Looking for GPU support for building an online demo: https://huggingface.co/spaces/huggingface/InferenceSupport/discussions/2602

\n","updatedAt":"2025-06-23T04:28:17.120Z","author":{"_id":"638ee900ee7e45e0474a5712","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg","fullname":"Yukun Huang","name":"KevinHuang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":7}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7375215291976929},"editors":["KevinHuang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg"],"reactions":[],"isReport":false}},{"id":"685a0114b119c595ebccc47b","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":264},"createdAt":"2025-06-24T01:36:20.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [Advancing high-fidelity 3D and Texture Generation with 2.5D latents](https://huggingface.co/papers/2505.21050) (2025)\n* [UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation](https://huggingface.co/papers/2505.24521) (2025)\n* [SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis](https://huggingface.co/papers/2506.10981) (2025)\n* [EX-4D: EXtreme Viewpoint 4D Video Synthesis via Depth Watertight Mesh](https://huggingface.co/papers/2506.05554) (2025)\n* [Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets](https://huggingface.co/papers/2505.07747) (2025)\n* [NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation](https://huggingface.co/papers/2506.07698) (2025)\n* [Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation](https://huggingface.co/papers/2506.04225) (2025)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2025-06-24T01:36:20.098Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":264}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6755871772766113},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2506.17206","authors":[{"_id":"6858c5b5c0c8e29df8ea3c95","user":{"_id":"638ee900ee7e45e0474a5712","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg","isPro":false,"fullname":"Yukun Huang","user":"KevinHuang","type":"user"},"name":"Yukun Huang","status":"claimed_verified","statusLastChangedAt":"2025-06-24T08:10:01.006Z","hidden":false},{"_id":"6858c5b5c0c8e29df8ea3c96","name":"Yanning Zhou","hidden":false},{"_id":"6858c5b5c0c8e29df8ea3c97","name":"Jianan Wang","hidden":false},{"_id":"6858c5b5c0c8e29df8ea3c98","name":"Kaiyi Huang","hidden":false},{"_id":"6858c5b5c0c8e29df8ea3c99","name":"Xihui Liu","hidden":false}],"publishedAt":"2025-06-20T17:55:06.000Z","submittedOnDailyAt":"2025-06-23T01:41:47.575Z","title":"DreamCube: 3D Panorama Generation via Multi-plane Synchronization","submittedOnDailyBy":{"_id":"638ee900ee7e45e0474a5712","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg","isPro":false,"fullname":"Yukun Huang","user":"KevinHuang","type":"user"},"summary":"3D panorama synthesis is a promising yet challenging task that demands\nhigh-quality and diverse visual appearance and geometry of the generated\nomnidirectional content. Existing methods leverage rich image priors from\npre-trained 2D foundation models to circumvent the scarcity of 3D panoramic\ndata, but the incompatibility between 3D panoramas and 2D single views limits\ntheir effectiveness. In this work, we demonstrate that by applying multi-plane\nsynchronization to the operators from 2D foundation models, their capabilities\ncan be seamlessly extended to the omnidirectional domain. Based on this design,\nwe further introduce DreamCube, a multi-plane RGB-D diffusion model for 3D\npanorama generation, which maximizes the reuse of 2D foundation model priors to\nachieve diverse appearances and accurate geometry while maintaining multi-view\nconsistency. Extensive experiments demonstrate the effectiveness of our\napproach in panoramic image generation, panoramic depth estimation, and 3D\nscene generation.","upvotes":23,"discussionId":"6858c5b6c0c8e29df8ea3c9a","projectPage":"https://yukun-huang.github.io/DreamCube/","githubRepo":"https://github.com/yukun-huang/DreamCube","ai_summary":"Multi-plane synchronization extends 2D foundation models to 3D panorama generation, introducing DreamCube to achieve diverse appearances and accurate geometry.","ai_keywords":["multi-plane synchronization","2D foundation models","DreamCube","RGB-D diffusion model","panoramic image generation","panoramic depth estimation","3D scene generation"],"githubStars":142},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"638ee900ee7e45e0474a5712","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638ee900ee7e45e0474a5712/KLli_eCbWwffKR7oLDmV3.jpeg","isPro":false,"fullname":"Yukun Huang","user":"KevinHuang","type":"user"},{"_id":"6427e08288215cee63b1c44d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6427e08288215cee63b1c44d/rzaG978FF-ywzicWNl_xl.jpeg","isPro":false,"fullname":"yao teng","user":"tytyt","type":"user"},{"_id":"64105a6d14215c0775dfdd14","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64105a6d14215c0775dfdd14/-VX-cUYOLjHIg7QnWhRGG.jpeg","isPro":false,"fullname":"Jiwen Yu","user":"VictorYuki","type":"user"},{"_id":"60d045c4778bafd0fbcfa3f5","avatarUrl":"/avatars/0cc0c2739c1934430ea09df7e9668c80.svg","isPro":false,"fullname":"Yi Chen","user":"ChenYi99","type":"user"},{"_id":"637cba13b8e573d75be96ea6","avatarUrl":"/avatars/5eca230e63d66947b2a05c1ff964a96c.svg","isPro":false,"fullname":"Nina","user":"NinaKarine","type":"user"},{"_id":"64b4eecf2fc8324fcb63b404","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b4eecf2fc8324fcb63b404/zGYqYVB4-o-GBMybJ8CDA.png","isPro":false,"fullname":"Yunhan Yang","user":"yhyang-myron","type":"user"},{"_id":"6365dd6fe7a78348d825b56f","avatarUrl":"/avatars/ba692bacea4ecb547854de1c3d539640.svg","isPro":false,"fullname":"Josh Fourie","user":"JoshFourie","type":"user"},{"_id":"672a037c19f1f942483f680c","avatarUrl":"/avatars/a48464044e9eb11a2bc062be05d9aa9a.svg","isPro":false,"fullname":"qiulu","user":"qiulu66","type":"user"},{"_id":"6342796a0875f2c99cfd313b","avatarUrl":"/avatars/98575092404c4197b20c929a6499a015.svg","isPro":false,"fullname":"Yuseung \"Phillip\" Lee","user":"phillipinseoul","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"668125557b50b433cda2a211","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/668125557b50b433cda2a211/j3z3wT5Rv9IyUKtbzQpnc.png","isPro":false,"fullname":"Tianwei Xiong","user":"YuuTennYi","type":"user"},{"_id":"638f308fc4444c6ca870b60a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638f308fc4444c6ca870b60a/Q11NK-8-JbiilJ-vk2LAR.png","isPro":true,"fullname":"Linoy Tsaban","user":"linoyts","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">

Papers

arxiv:2506.17206

DreamCube: 3D Panorama Generation via Multi-plane Synchronization

Published on Jun 20

· Submitted by

Yukun Huang on Jun 23

Upvote

Authors:

Yukun Huang ,

Abstract

Multi-plane synchronization extends 2D foundation models to 3D panorama generation, introducing DreamCube to achieve diverse appearances and accurate geometry.

AI-generated summary

3D panorama synthesis is a promising yet challenging task that demands high-quality and diverse visual appearance and geometry of the generated omnidirectional content. Existing methods leverage rich image priors from pre-trained 2D foundation models to circumvent the scarcity of 3D panoramic data, but the incompatibility between 3D panoramas and 2D single views limits their effectiveness. In this work, we demonstrate that by applying multi-plane synchronization to the operators from 2D foundation models, their capabilities can be seamlessly extended to the omnidirectional domain. Based on this design, we further introduce DreamCube, a multi-plane RGB-D diffusion model for 3D panorama generation, which maximizes the reuse of 2D foundation model priors to achieve diverse appearances and accurate geometry while maintaining multi-view consistency. Extensive experiments demonstrate the effectiveness of our approach in panoramic image generation, panoramic depth estimation, and 3D scene generation.