{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KWV56JTVDMPYWJ4DGI6WBSDUZ6","short_pith_number":"pith:KWV56JTV","schema_version":"1.0","canonical_sha256":"55abdf26751b1f8b2783323d60c874cfb620d98457a080f542f1e6472f8b3ec9","source":{"kind":"arxiv","id":"2309.16653","version":2},"attestation_state":"computed","paper":{"title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DreamGaussian generates high-quality textured 3D meshes from a single image in two minutes.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Zeng, Hang Zhou, Jiawei Ren, Jiaxiang Tang, Ziwei Liu","submitted_at":"2023-09-28T17:55:05Z","abstract_excerpt":"Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their practical usage. In this paper, we propose DreamGaussian, a novel 3D content generation framework that achieves both efficiency and quality simultaneously. Our key insight is to design a generative 3D Gaussian Splatting model with companioned mesh extraction and texture refinement in UV space. In contrast to the occupancy pruning used in Neural Rad"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2309.16653","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-28T17:55:05Z","cross_cats_sorted":[],"title_canon_sha256":"1014e14e823d5ff27f9cdf733732de8e7ed817fb46ca9d908d186bda109891e9","abstract_canon_sha256":"359d690044cb76f12cf507ff02a7c4db69db10f39f1ba33bfd238710d69c98b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.216446Z","signature_b64":"dtmLwBsAN90LYAzpqxsFGZKUlW9W1/o7YYkoyL5wVIK9vq07YzM26sl3x4Unr8gxPASOnBIZXc0uYgu31LF0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55abdf26751b1f8b2783323d60c874cfb620d98457a080f542f1e6472f8b3ec9","last_reissued_at":"2026-05-17T23:38:48.215978Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.215978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DreamGaussian generates high-quality textured 3D meshes from a single image in two minutes.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Zeng, Hang Zhou, Jiawei Ren, Jiaxiang Tang, Ziwei Liu","submitted_at":"2023-09-28T17:55:05Z","abstract_excerpt":"Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their practical usage. In this paper, we propose DreamGaussian, a novel 3D content generation framework that achieves both efficiency and quality simultaneously. Our key insight is to design a generative 3D Gaussian Splatting model with companioned mesh extraction and texture refinement in UV space. In contrast to the occupancy pruning used in Neural Rad"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"DreamGaussian produces high-quality textured meshes in just 2 minutes from a single-view image, achieving approximately 10 times acceleration compared to existing methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Progressive densification of 3D Gaussians converges significantly faster for 3D generative tasks than occupancy pruning in NeRFs, and the subsequent mesh extraction plus UV refinement preserves generation quality without introducing artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DreamGaussian generates high-quality textured 3D meshes from a single image in two minutes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"030df4914c93fc89db9b3ad2e1511aba13732f7313babd6496453919485e77ee"},"source":{"id":"2309.16653","kind":"arxiv","version":2},"verdict":{"id":"32d789cb-5eeb-450a-a4d1-16746aa1b10c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T10:14:27.091173Z","strongest_claim":"DreamGaussian produces high-quality textured meshes in just 2 minutes from a single-view image, achieving approximately 10 times acceleration compared to existing methods.","one_line_summary":"DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Progressive densification of 3D Gaussians converges significantly faster for 3D generative tasks than occupancy pruning in NeRFs, and the subsequent mesh extraction plus UV refinement preserves generation quality without introducing artifacts.","pith_extraction_headline":"DreamGaussian generates high-quality textured 3D meshes from a single image in two minutes."},"references":{"count":158,"sample":[{"doi":"","year":null,"title":"ToG , publisher =","work_id":"71e36c5b-fc9b-4a78-a830-3cb7fd1fee63","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Modular Primitives for High-Performance Differentiable Rendering , author =","work_id":"5f7277bf-80f2-4697-95d1-62814689e306","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis , author =","work_id":"2a6d1d0a-8afa-4015-8f81-77cfaf7da7c7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Zero-1-to-3: Zero-shot one image to 3d object , author =","work_id":"37e456e2-6341-4e7c-a1b1-e1585652b0a4","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Sdedit: Guided image synthesis and editing with stochastic differential equations , author =","work_id":"78e1536f-60f2-46d2-bad8-cc3d45288e8e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":158,"snapshot_sha256":"27f072926f809f25f3e178560e28584cf281230a860adf40da089d2e5f5c6662","internal_anchors":9},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bdef50b713d19c0f85a957d7aac015295ee09048813d4e689f55c2315dbbc759"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.16653","created_at":"2026-05-17T23:38:48.216054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16653v2","created_at":"2026-05-17T23:38:48.216054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16653","created_at":"2026-05-17T23:38:48.216054+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWV56JTVDMPY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWV56JTVDMPYWJ4D","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWV56JTV","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":37,"internal_anchor_count":37,"sample":[{"citing_arxiv_id":"2412.13111","citing_title":"Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2501.12202","citing_title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","ref_index":87,"is_internal_anchor":true},{"citing_arxiv_id":"2503.06740","citing_title":"Diffusion Models are Secretly Zero-Shot 3DGS Harmonizers","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2504.02316","citing_title":"ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2504.13109","citing_title":"UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07287","citing_title":"SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2508.01014","citing_title":"Hestia: Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstruction","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2511.16766","citing_title":"SVG360: Editable Multiview Vector Graphics from a Single SVG","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20872","citing_title":"CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19949","citing_title":"Feed-Forward Gaussian Splatting from Sparse Aerial Views","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2405.10314","citing_title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16807","citing_title":"DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2509.07435","citing_title":"DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2310.15110","citing_title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2406.02509","citing_title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2601.00285","citing_title":"SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2403.02151","citing_title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2602.01674","citing_title":"VRGaussianAvatar: Integrating 3D Gaussian Avatars into VR","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":161,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13600","citing_title":"Sparse Code Uplifting for Efficient 3D Language Gaussian Splatting","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":161,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02736","citing_title":"THOM: Generating Physically Plausible Hand-Object Meshes From Text","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02867","citing_title":"HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04016","citing_title":"HOIGS: Human-Object Interaction Gaussian Splatting","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWV56JTVDMPYWJ4DGI6WBSDUZ6","json":"https://pith.science/pith/KWV56JTVDMPYWJ4DGI6WBSDUZ6.json","graph_json":"https://pith.science/api/pith-number/KWV56JTVDMPYWJ4DGI6WBSDUZ6/graph.json","events_json":"https://pith.science/api/pith-number/KWV56JTVDMPYWJ4DGI6WBSDUZ6/events.json","paper":"https://pith.science/paper/KWV56JTV"},"agent_actions":{"view_html":"https://pith.science/pith/KWV56JTVDMPYWJ4DGI6WBSDUZ6","download_json":"https://pith.science/pith/KWV56JTVDMPYWJ4DGI6WBSDUZ6.json","view_paper":"https://pith.science/paper/KWV56JTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16653&json=true","fetch_graph":"https://pith.science/api/pith-number/KWV56JTVDMPYWJ4DGI6WBSDUZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/KWV56JTVDMPYWJ4DGI6WBSDUZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWV56JTVDMPYWJ4DGI6WBSDUZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWV56JTVDMPYWJ4DGI6WBSDUZ6/action/storage_attestation","attest_author":"https://pith.science/pith/KWV56JTVDMPYWJ4DGI6WBSDUZ6/action/author_attestation","sign_citation":"https://pith.science/pith/KWV56JTVDMPYWJ4DGI6WBSDUZ6/action/citation_signature","submit_replication":"https://pith.science/pith/KWV56JTVDMPYWJ4DGI6WBSDUZ6/action/replication_record"}},"created_at":"2026-05-17T23:38:48.216054+00:00","updated_at":"2026-05-17T23:38:48.216054+00:00"}