We built Photoshop's magic wand for 3D Gaussian Splatting. ✨</p>\n<p>Meet 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐒𝐞𝐥𝐞𝐜𝐭𝐨𝐫 🖌️ — scribble on one view, and the whole 3D object pops out of the scene. Same gesture you'd use to select a flower in a photo, except the canvas is in 3D space and what you get back is a real 3D asset.</p>\n<p>Forget about renting GPU servers to deploy heavy 3D segmentation models. That's a phone doing it, live 📱👇</p>\n<p><video src=\"https://cdn-uploads.huggingface.co/production/uploads/6719d7b6248e67e1a915d9b8/5TvvdMDk8s82PxkvNTN9H.mp4\" controls=\"\" class=\"max-w-full!\"></video></p>","updatedAt":"2026-08-07T22:42:54.456Z","author":{"_id":"6719d7b6248e67e1a915d9b8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6719d7b6248e67e1a915d9b8/XcxMnbh_y-yZ-eH3au6LW.jpeg","fullname":"YuhengLiu","name":"Yuheng02","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8070180416107178},"editors":["Yuheng02"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6719d7b6248e67e1a915d9b8/XcxMnbh_y-yZ-eH3au6LW.jpeg"],"reactions":[],"isReport":false}},{"id":"6a76878b14fd2a1046f0c5e2","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":378,"isUserFollowing":false},"createdAt":"2026-08-08T01:34:03.000Z","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* [Intrinsic 4D Gaussian Segmentation from Scene Cues](https://huggingface.co/papers/2606.18623) (2026)\n* [Consistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinement](https://huggingface.co/papers/2607.01708) (2026)\n* [Super-Gaussian: Interactive Scene Editing for 3D Gaussian Splatting and NLI-Based Volume Visualization in Virtual Reality](https://huggingface.co/papers/2608.04475) (2026)\n* [OutLangSplat: 3D Language Gaussian Splatting for UAV Outdoor Scenes](https://huggingface.co/papers/2608.04560) (2026)\n* [ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting](https://huggingface.co/papers/2607.18801) (2026)\n* [Ground4D: Consistency-Aware 4D Reconstruction from Monocular Video](https://huggingface.co/papers/2606.28828) (2026)\n* [Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images](https://huggingface.co/papers/2607.01633) (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/2606.18623\">Intrinsic 4D Gaussian Segmentation from Scene Cues</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2607.01708\">Consistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinement</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2608.04475\">Super-Gaussian: Interactive Scene Editing for 3D Gaussian Splatting and NLI-Based Volume Visualization in Virtual Reality</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2608.04560\">OutLangSplat: 3D Language Gaussian Splatting for UAV Outdoor Scenes</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2607.18801\">ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.28828\">Ground4D: Consistency-Aware 4D Reconstruction from Monocular Video</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2607.01633\">Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images</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":"2026-08-08T01:34:03.258Z","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":378,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7319480180740356},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.01492","authors":[{"_id":"6a765ecc8e9301703eaa5900","name":"Baihan Yang","hidden":false},{"_id":"6a765ecc8e9301703eaa5901","name":"Tiexin Li","hidden":false},{"_id":"6a765ecc8e9301703eaa5902","user":{"_id":"6719d7b6248e67e1a915d9b8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6719d7b6248e67e1a915d9b8/XcxMnbh_y-yZ-eH3au6LW.jpeg","isPro":false,"fullname":"YuhengLiu","user":"Yuheng02","type":"user","name":"Yuheng02"},"name":"Yuheng Liu","status":"claimed_verified","statusLastChangedAt":"2026-08-08T00:45:04.567Z","hidden":false},{"_id":"6a765ecc8e9301703eaa5903","name":"Xin Lin","hidden":false},{"_id":"6a765ecc8e9301703eaa5904","name":"Xinke Li","hidden":false},{"_id":"6a765ecc8e9301703eaa5905","name":"Xiaohui Xie","hidden":false},{"_id":"6a765ecc8e9301703eaa5906","name":"Truong Nguyen","hidden":false}],"publishedAt":"2026-08-02T00:00:00.000Z","submittedOnDailyAt":"2026-08-07T00:00:00.000Z","title":"GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization","submittedOnDailyBy":{"_id":"6719d7b6248e67e1a915d9b8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6719d7b6248e67e1a915d9b8/XcxMnbh_y-yZ-eH3au6LW.jpeg","isPro":false,"fullname":"YuhengLiu","user":"Yuheng02","type":"user","name":"Yuheng02"},"summary":"Selecting a complete 3D object from a reconstructed scene with minimal user effort is essential for practical scene editing and embodied interaction. Existing 3DGS-based methods either retrain the Gaussian representation to embed per-object labels, or build dense multi-view SAM observations, both requiring heavy computation and dense viewpoint coverage that is rarely available in practice. We present GaussianSelector, a training-free framework for interactive 3D object selection from sparse views and sparse scribble guidance. Operating directly on native Gaussian primitives, we coarsen dense Gaussians into geometrically coherent superpoints and construct a continuity-weighted graph using appearance and spatial cues. Sparse user scribbles are lifted into 3D via visibility-aware transmittance coverage, and selection is solved as a global graph-cut energy minimization that propagates sparse evidence to a complete 3D object. This design naturally supports multi-round refinement, where users iteratively correct the selection from additional viewpoints to progressively improve the result. Experiments demonstrate that GaussianSelector achieves competitive selection quality against state-of-the-art multi-view SAM-based methods, while requiring significantly fewer interaction views and substantially lower computational overhead. These properties make it well suited for human-in-the-loop 3D scene editing and 3D asset extraction in real-world deployment scenarios.","upvotes":4,"discussionId":"6a765ecc8e9301703eaa5907","projectPage":"https://lllab.org/blog/GaussianSelector-Implementation-Notes-What-Didn-t-Fit-in-the-Paper","organization":{"_id":"6a377ac0539cf0e2e8f02877","name":"lllab","fullname":"LL Lab","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6719d7b6248e67e1a915d9b8/5QhTXTUfpcVk-aE1fHxsV.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6a742a683d438d7c49c8eaa2","avatarUrl":"/avatars/f7828c23fad2988df910b983e5f466b2.svg","isPro":false,"fullname":"Benjamin Nathaniel Hathorne","user":"Entmarch","type":"user"},{"_id":"6a69ec703e202470681e0dad","avatarUrl":"/avatars/1812d9bb94b84c2d46903a3304e380b5.svg","isPro":false,"fullname":"Michael Lopez","user":"lopez-michael","type":"user"},{"_id":"6a6c88ff4804b5ea70e0d351","avatarUrl":"/avatars/7280b26f4ae2fe5b33ffd15b92980125.svg","isPro":false,"fullname":"Susan Johnson","user":"Atlas-Susan","type":"user"},{"_id":"6a6dcab1e1c088f5242818bd","avatarUrl":"/avatars/16944b49b3a66aca9bf9ab88da508f79.svg","isPro":false,"fullname":"Sarah Brown","user":"PrismRidge","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6a377ac0539cf0e2e8f02877","name":"lllab","fullname":"LL Lab","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6719d7b6248e67e1a915d9b8/5QhTXTUfpcVk-aE1fHxsV.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.01492.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2608.01492 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.01492 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2608.01492 in a Space README.md to link it from this page.