{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L3ZL5DRKWPDO45LHBAZP2XETPS","short_pith_number":"pith:L3ZL5DRK","schema_version":"1.0","canonical_sha256":"5ef2be8e2ab3c6ee75670832fd5c937c8afea21186d14aefd911f61b56a029ff","source":{"kind":"arxiv","id":"2311.06214","version":2},"attestation_state":"computed","paper":{"title":"Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fujun Luan, Greg Shakhnarovich, Hao Tan, Jiahao Li, Kai Zhang, Kalyan Sunkavalli, Sai Bi, Yicong Hong, Yinghao Xu, Zexiang Xu","submitted_at":"2023-11-10T18:03:44Z","abstract_excerpt":"Text-to-3D with diffusion models has achieved remarkable progress in recent years. However, existing methods either rely on score distillation-based optimization which suffer from slow inference, low diversity and Janus problems, or are feed-forward methods that generate low-quality results due to the scarcity of 3D training data. In this paper, we propose Instant3D, a novel method that generates high-quality and diverse 3D assets from text prompts in a feed-forward manner. We adopt a two-stage paradigm, which first generates a sparse set of four structured and consistent views from text in on"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.06214","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-10T18:03:44Z","cross_cats_sorted":[],"title_canon_sha256":"4e37ecb58ffcb45d923b03134d4ec29e008635f839750f4734402ea10ba5621a","abstract_canon_sha256":"43cd1eded16e0802a5eff92ceca9ad52f2fbe9a4315efbb03623ed0a02684270"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:02.987120Z","signature_b64":"BhNwDoj9SJNbM8K7rbGtMtQXBz75Hs4kzUfcr7B0fwFmLlR6ouW9032am5ynMhOCQ2ICoetrjpb1pM6XREwDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ef2be8e2ab3c6ee75670832fd5c937c8afea21186d14aefd911f61b56a029ff","last_reissued_at":"2026-07-05T07:16:02.986606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:02.986606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fujun Luan, Greg Shakhnarovich, Hao Tan, Jiahao Li, Kai Zhang, Kalyan Sunkavalli, Sai Bi, Yicong Hong, Yinghao Xu, Zexiang Xu","submitted_at":"2023-11-10T18:03:44Z","abstract_excerpt":"Text-to-3D with diffusion models has achieved remarkable progress in recent years. However, existing methods either rely on score distillation-based optimization which suffer from slow inference, low diversity and Janus problems, or are feed-forward methods that generate low-quality results due to the scarcity of 3D training data. In this paper, we propose Instant3D, a novel method that generates high-quality and diverse 3D assets from text prompts in a feed-forward manner. We adopt a two-stage paradigm, which first generates a sparse set of four structured and consistent views from text in on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06214","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.06214/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2311.06214","created_at":"2026-07-05T07:16:02.986679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06214v2","created_at":"2026-07-05T07:16:02.986679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06214","created_at":"2026-07-05T07:16:02.986679+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3ZL5DRKWPDO","created_at":"2026-07-05T07:16:02.986679+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3ZL5DRKWPDO45LH","created_at":"2026-07-05T07:16:02.986679+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3ZL5DRK","created_at":"2026-07-05T07:16:02.986679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24206","citing_title":"Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10142","citing_title":"DB-3DME: From Dataset to Benchmark for Human-aligned Automatic 3D Mesh Evaluation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04945","citing_title":"STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32036","citing_title":"PointSplat: Compact Gaussian Splatting via Human-Centric Prediction","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31466","citing_title":"VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14671","citing_title":"ART: Articulated Reconstruction Transformer","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21121","citing_title":"ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15843","citing_title":"WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2405.10314","citing_title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07435","citing_title":"DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2502.06608","citing_title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2403.02151","citing_title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2601.11194","citing_title":"ATATA: One Algorithm to Align Them All","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04400","citing_title":"LRM: Large Reconstruction Model for Single Image to 3D","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01479","citing_title":"UniRecGen: Unifying Multi-View 3D Reconstruction and Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27504","citing_title":"REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26917","citing_title":"AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04412","citing_title":"Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20093","citing_title":"FurnSet: Exploiting Repeats for 3D Scene Reconstruction","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19257","citing_title":"Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L3ZL5DRKWPDO45LHBAZP2XETPS","json":"https://pith.science/pith/L3ZL5DRKWPDO45LHBAZP2XETPS.json","graph_json":"https://pith.science/api/pith-number/L3ZL5DRKWPDO45LHBAZP2XETPS/graph.json","events_json":"https://pith.science/api/pith-number/L3ZL5DRKWPDO45LHBAZP2XETPS/events.json","paper":"https://pith.science/paper/L3ZL5DRK"},"agent_actions":{"view_html":"https://pith.science/pith/L3ZL5DRKWPDO45LHBAZP2XETPS","download_json":"https://pith.science/pith/L3ZL5DRKWPDO45LHBAZP2XETPS.json","view_paper":"https://pith.science/paper/L3ZL5DRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06214&json=true","fetch_graph":"https://pith.science/api/pith-number/L3ZL5DRKWPDO45LHBAZP2XETPS/graph.json","fetch_events":"https://pith.science/api/pith-number/L3ZL5DRKWPDO45LHBAZP2XETPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3ZL5DRKWPDO45LHBAZP2XETPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3ZL5DRKWPDO45LHBAZP2XETPS/action/storage_attestation","attest_author":"https://pith.science/pith/L3ZL5DRKWPDO45LHBAZP2XETPS/action/author_attestation","sign_citation":"https://pith.science/pith/L3ZL5DRKWPDO45LHBAZP2XETPS/action/citation_signature","submit_replication":"https://pith.science/pith/L3ZL5DRKWPDO45LHBAZP2XETPS/action/replication_record"}},"created_at":"2026-07-05T07:16:02.986679+00:00","updated_at":"2026-07-05T07:16:02.986679+00:00"}