3D vision has rapidly evolved, driven by increasingly diverse data representations, learning paradigms, and modeling strategies. Yet the field remains fragmented across representations and benchmarks, making it difficult to develop unified perspectives on efficiency, fidelity, and scalability. This work provides a data-centric taxonomy of 3D vision that connects geometric representations, datasets, learning frameworks, and applications within a single conceptual map. We begin by analysing the principal structural representations of 3D data--point clouds, meshes, voxels, and 3D Gaussians--along with their acquisition pipelines. We then examine how dataset design, benchmark construction, and supervision regimes shape recent advances, spanning 2D-supervised 3D learning, implicit neural representations, and 4D world modeling. Through this integrative lens, we clarify the relationships among representations, learning paradigms, and downstream tasks in reconstruction, generation, and video modeling, offering a consolidated view of emerging trends toward balancing efficiency and fidelity and toward multimodal geometric grounding.</p>\n","updatedAt":"2026-06-08T18:06:06.586Z","author":{"_id":"642447e873f7a0d40b30d677","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/642447e873f7a0d40b30d677/hbUnfIhKZCeSSPv9wGAzk.png","fullname":"LZX","name":"zli12321","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":8,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8954479694366455},"editors":["zli12321"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/642447e873f7a0d40b30d677/hbUnfIhKZCeSSPv9wGAzk.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.04291","authors":[{"_id":"6a2356d4e4c258a029491813","name":"Hongyang Du","hidden":false},{"_id":"6a2356d4e4c258a029491814","name":"Zongxia Li","hidden":false},{"_id":"6a2356d4e4c258a029491815","name":"Dawei Liu","hidden":false},{"_id":"6a2356d4e4c258a029491816","name":"Runhao Li","hidden":false},{"_id":"6a2356d4e4c258a029491817","name":"Haoyuan Song","hidden":false},{"_id":"6a2356d4e4c258a029491818","name":"Qingyu Zhang","hidden":false},{"_id":"6a2356d4e4c258a029491819","name":"Yubo Wang","hidden":false},{"_id":"6a2356d4e4c258a02949181a","name":"Jingcheng Ni","hidden":false},{"_id":"6a2356d4e4c258a02949181b","name":"Shihang Gui","hidden":false},{"_id":"6a2356d4e4c258a02949181c","name":"Congchao Dong","hidden":false},{"_id":"6a2356d4e4c258a02949181d","name":"Tao Hu","hidden":false}],"publishedAt":"2026-06-02T00:00:00.000Z","submittedOnDailyAt":"2026-06-08T00:00:00.000Z","title":"A Cookbook of 3D Vision: Data, Learning Paradigms, and Application","submittedOnDailyBy":{"_id":"642447e873f7a0d40b30d677","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/642447e873f7a0d40b30d677/hbUnfIhKZCeSSPv9wGAzk.png","isPro":false,"fullname":"LZX","user":"zli12321","type":"user","name":"zli12321"},"summary":"3D vision has rapidly evolved, driven by increasingly diverse data representations, learning paradigms, and modeling strategies. Yet the field remains fragmented across representations and benchmarks, making it difficult to develop unified perspectives on efficiency, fidelity, and scalability. This work provides a data-centric taxonomy of 3D vision that connects geometric representations, datasets, learning frameworks, and applications within a single conceptual map. We begin by analysing the principal structural representations of 3D data--point clouds, meshes, voxels, and 3D Gaussians--along with their acquisition pipelines. We then examine how dataset design, benchmark construction, and supervision regimes shape recent advances, spanning 2D-supervised 3D learning, implicit neural representations, and 4D world modeling. Through this integrative lens, we clarify the relationships among representations, learning paradigms, and downstream tasks in reconstruction, generation, and video modeling, offering a consolidated view of emerging trends toward balancing efficiency and fidelity and toward multimodal geometric grounding.","upvotes":2,"discussionId":"6a2356d4e4c258a02949181e","ai_summary":"3D vision research is organized through a taxonomy connecting geometric representations, datasets, learning frameworks, and applications across reconstruction, generation, and video modeling tasks.","ai_keywords":["point clouds","meshes","voxels","3D Gaussians","implicit neural representations","4D world modeling","geometric representations","dataset design","benchmark construction","supervision regimes","2D-supervised 3D learning","reconstruction","generation","video modeling","multimodal geometric grounding"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","organization":{"_id":"620e88a5b6c1d205f69ed06b","name":"brownu","fullname":"Brown University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/63e8e8f2ccae1fe5c61ad852/tBcw2mYI7wPCW319qd6F6.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"642447e873f7a0d40b30d677","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/642447e873f7a0d40b30d677/hbUnfIhKZCeSSPv9wGAzk.png","isPro":false,"fullname":"LZX","user":"zli12321","type":"user"},{"_id":"667230de876f9f27d6b097ea","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/667230de876f9f27d6b097ea/hhz4nfTUdAAMIPXw3A342.jpeg","isPro":false,"fullname":"Hongyang Du","user":"Hongyang-Du","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"620e88a5b6c1d205f69ed06b","name":"brownu","fullname":"Brown University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/63e8e8f2ccae1fe5c61ad852/tBcw2mYI7wPCW319qd6F6.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.04291.md"}">
A Cookbook of 3D Vision: Data, Learning Paradigms, and Application
Published on Jun 2
· Submitted by LZX on Jun 8 Authors: ,
,
,
,
,
,
,
,
,
,
Abstract
3D vision research is organized through a taxonomy connecting geometric representations, datasets, learning frameworks, and applications across reconstruction, generation, and video modeling tasks.
3D vision has rapidly evolved, driven by increasingly diverse data representations, learning paradigms, and modeling strategies. Yet the field remains fragmented across representations and benchmarks, making it difficult to develop unified perspectives on efficiency, fidelity, and scalability. This work provides a data-centric taxonomy of 3D vision that connects geometric representations, datasets, learning frameworks, and applications within a single conceptual map. We begin by analysing the principal structural representations of 3D data--point clouds, meshes, voxels, and 3D Gaussians--along with their acquisition pipelines. We then examine how dataset design, benchmark construction, and supervision regimes shape recent advances, spanning 2D-supervised 3D learning, implicit neural representations, and 4D world modeling. Through this integrative lens, we clarify the relationships among representations, learning paradigms, and downstream tasks in reconstruction, generation, and video modeling, offering a consolidated view of emerging trends toward balancing efficiency and fidelity and toward multimodal geometric grounding.
Community
3D vision has rapidly evolved, driven by increasingly diverse data representations, learning paradigms, and modeling strategies. Yet the field remains fragmented across representations and benchmarks, making it difficult to develop unified perspectives on efficiency, fidelity, and scalability. This work provides a data-centric taxonomy of 3D vision that connects geometric representations, datasets, learning frameworks, and applications within a single conceptual map. We begin by analysing the principal structural representations of 3D data--point clouds, meshes, voxels, and 3D Gaussians--along with their acquisition pipelines. We then examine how dataset design, benchmark construction, and supervision regimes shape recent advances, spanning 2D-supervised 3D learning, implicit neural representations, and 4D world modeling. Through this integrative lens, we clarify the relationships among representations, learning paradigms, and downstream tasks in reconstruction, generation, and video modeling, offering a consolidated view of emerging trends toward balancing efficiency and fidelity and toward multimodal geometric grounding.
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/2606.04291 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.04291 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.04291 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.