TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive</p>\n<p>Accepted to ECCV 2026.</p>\n","updatedAt":"2026-07-01T05:09:00.552Z","author":{"_id":"64e93050e574e31915800b5e","avatarUrl":"/avatars/7ff4adb4ffb8b47fe293d0b424baf5d1.svg","fullname":"Srikumar Sastry","name":"Srikumar26","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7303754091262817},"editors":["Srikumar26"],"editorAvatarUrls":["/avatars/7ff4adb4ffb8b47fe293d0b424baf5d1.svg"],"reactions":[],"isReport":false}},{"id":"6a45c32a6ac8c491c6e17220","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":372,"isUserFollowing":false},"createdAt":"2026-07-02T01:47:22.000Z","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* [MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modeling](https://huggingface.co/papers/2605.20090) (2026)\n* [Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization](https://huggingface.co/papers/2606.30576) (2026)\n* [Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image](https://huggingface.co/papers/2606.24138) (2026)\n* [RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction](https://huggingface.co/papers/2605.26862) (2026)\n* [VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement](https://huggingface.co/papers/2605.17102) (2026)\n* [AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond](https://huggingface.co/papers/2605.26113) (2026)\n* [UAV as Urban Construction Change Monitor: A New Benchmark and Change Captioning Model](https://huggingface.co/papers/2605.04409) (2026)\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":"<p>This is an automated message from the <a href=\"https://huggingface.co/librarian-bots\">Librarian Bot</a>. I found the following papers similar to this paper. </p>\n<p>The following papers were recommended by the Semantic Scholar API </p>\n<ul>\n<li><a href=\"https://huggingface.co/papers/2605.20090\">MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modeling</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.30576\">Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.24138\">Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.26862\">RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.17102\">VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.26113\">AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.04409\">UAV as Urban Construction Change Monitor: A New Benchmark and Change Captioning Model</a> (2026)</li>\n</ul>\n<p> Please give a thumbs up to this comment if you found it helpful!</p>\n<p> If you want recommendations for any Paper on Hugging Face checkout <a href=\"https://huggingface.co/spaces/librarian-bots/recommend_similar_papers\">this</a> Space</p>\n<p> You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: <code>@librarian-bot recommend</code></p>\n","updatedAt":"2026-07-02T01:47:22.448Z","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":372,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7144231200218201},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.31029","authors":[{"_id":"6a44a08341f04ae4d7ad9856","name":"Brian Wei","hidden":false},{"_id":"6a44a08341f04ae4d7ad9857","name":"Srikumar Sastry","hidden":false},{"_id":"6a44a08341f04ae4d7ad9858","name":"Daniel Cher","hidden":false},{"_id":"6a44a08341f04ae4d7ad9859","name":"Eric Xing","hidden":false},{"_id":"6a44a08341f04ae4d7ad985a","name":"Nathan Jacobs","hidden":false}],"publishedAt":"2026-06-30T00:00:00.000Z","submittedOnDailyAt":"2026-07-01T00:00:00.000Z","title":"TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive","submittedOnDailyBy":{"_id":"64e93050e574e31915800b5e","avatarUrl":"/avatars/7ff4adb4ffb8b47fe293d0b424baf5d1.svg","isPro":false,"fullname":"Srikumar Sastry","user":"Srikumar26","type":"user","name":"Srikumar26"},"summary":"Generative models have achieved remarkable progress, yet applying them to satellite imagery remains challenging. Unlike natural imagery, satellite scenes are structured by spatially complex and semantically distinct geometries. Prior work addresses this complexity by adapting natural image frameworks using dense rasters or sparse prompts, trading off annotation cost and fidelity while breaking compatibility with vector primitives commonly used to represent geographic information. We introduce TerraDiT-Ω, a unified spatial control framework that generates satellite imagery directly from any native geospatial primitive. By jointly leveraging precise annotations (polygons, polylines) and coarser ones (bounding boxes, points), the model supports controllable layouts across varying annotation budgets, broadening applicability to design tasks such as urban planning while remaining naturally compatible with end-to-end GeoAI workflows. To effectively leverage these primitives during generation, we propose Geometry-Aware Local Attention, a conditioning mechanism that injects explicit geometric cues into the attention space. Across all conditioning formats, our approach consistently outperforms both dense-control and sparse-control baselines. Furthermore, this flexibility enables controllable synthetic data augmentation using a single generative model, improving downstream performance on land-cover segmentation, object detection, road graph extraction, and scene classification. Code, data, and weights are available at https://github.com/mvrl/TerraDiT.","upvotes":2,"discussionId":"6a44a08341f04ae4d7ad985b","projectPage":"https://brian-j-wei.github.io/terradit-omega","githubRepo":"https://github.com/mvrl/TerraDiT","githubRepoAddedBy":"user","ai_summary":"TerraDiT-Ω generates satellite imagery from native geospatial primitives using Geometry-Aware Local Attention, enabling flexible conditioning and improved downstream geospatial tasks.","ai_keywords":["generative models","satellite imagery","geospatial primitives","Geometry-Aware Local Attention","controllable layouts","land-cover segmentation","object detection","road graph extraction","scene classification"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":1,"organization":{"_id":"652fef7c8f61edf213bbbab2","name":"MVRL","fullname":"Multimodal Vision Research Laboratory @ WashU","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/652ffca9729ec1a37e4e7915/P94G4gdINp2-T2IImrUg5.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64e93050e574e31915800b5e","avatarUrl":"/avatars/7ff4adb4ffb8b47fe293d0b424baf5d1.svg","isPro":false,"fullname":"Srikumar Sastry","user":"Srikumar26","type":"user"},{"_id":"66935bdc5489e4f73c76bc7b","avatarUrl":"/avatars/129d1e86bbaf764b507501f4feb177db.svg","isPro":false,"fullname":"Abidoye Aanuoluwapo","user":"Aanuoluwapo65","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"652fef7c8f61edf213bbbab2","name":"MVRL","fullname":"Multimodal Vision Research Laboratory @ WashU","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/652ffca9729ec1a37e4e7915/P94G4gdINp2-T2IImrUg5.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.31029.md","query":{}}">
TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive
Abstract
TerraDiT-Ω generates satellite imagery from native geospatial primitives using Geometry-Aware Local Attention, enabling flexible conditioning and improved downstream geospatial tasks.
Generative models have achieved remarkable progress, yet applying them to satellite imagery remains challenging. Unlike natural imagery, satellite scenes are structured by spatially complex and semantically distinct geometries. Prior work addresses this complexity by adapting natural image frameworks using dense rasters or sparse prompts, trading off annotation cost and fidelity while breaking compatibility with vector primitives commonly used to represent geographic information. We introduce TerraDiT-Ω, a unified spatial control framework that generates satellite imagery directly from any native geospatial primitive. By jointly leveraging precise annotations (polygons, polylines) and coarser ones (bounding boxes, points), the model supports controllable layouts across varying annotation budgets, broadening applicability to design tasks such as urban planning while remaining naturally compatible with end-to-end GeoAI workflows. To effectively leverage these primitives during generation, we propose Geometry-Aware Local Attention, a conditioning mechanism that injects explicit geometric cues into the attention space. Across all conditioning formats, our approach consistently outperforms both dense-control and sparse-control baselines. Furthermore, this flexibility enables controllable synthetic data augmentation using a single generative model, improving downstream performance on land-cover segmentation, object detection, road graph extraction, and scene classification. Code, data, and weights are available at https://github.com/mvrl/TerraDiT.
Community
TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive
Accepted to ECCV 2026.
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: @librarian-bot recommend
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2606.31029 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.31029 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.31029 in a Space README.md 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.