{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S765KQREDPHMBE4CBRBWGGVQH6","short_pith_number":"pith:S765KQRE","schema_version":"1.0","canonical_sha256":"97fdd542241bcec093820c43631ab03fb18386e82a7e239ca49e91e45b9d111d","source":{"kind":"arxiv","id":"2411.02293","version":5},"attestation_state":"computed","paper":{"title":"Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Chunchao Guo, Di Wang, Fan Yang, Hongxu Zhao, Huiwen Shi, Jiaao Yu, Jiacheng Wang, Jie Jiang, Jing Xu, Junta Wu, Lifu Wang, Qingxiang Lin, Shaoxiong Yang, Sicong Liu, Xianghui Yang, Xinhai Liu, Xinzhou Wang, Yihang Lian, Yong Yang, Yuhong Liu, Zebin He, Zhuo Chen","submitted_at":"2024-11-04T17:21:42Z","abstract_excerpt":"While 3D generative models have greatly improved artists' workflows, the existing diffusion models for 3D generation suffer from slow generation and poor generalization. To address this issue, we propose a two-stage approach named Hunyuan3D 1.0 including a lite version and a standard version, that both support text- and image-conditioned generation. In the first stage, we employ a multi-view diffusion model that efficiently generates multi-view RGB in approximately 4 seconds. These multi-view images capture rich details of the 3D asset from different viewpoints, relaxing the tasks from single-"},"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":"2411.02293","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T17:21:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4c9f9f56fb89998663fe6eeddb8b9f71cc7eb7436df1415311943eea6c9f074","abstract_canon_sha256":"2ca057f1b09b323f4dabe5b365856e86503f08f0ca8f01e5524230f071a5d64a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:19.422249Z","signature_b64":"rMbT8+hJSOZiOcX63piC1kgrAuNSlnC35B/3V0MTJd7+virpjVJzhtxaW6xjd9NJ6N+dyUWXorDNA7IXMAzECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97fdd542241bcec093820c43631ab03fb18386e82a7e239ca49e91e45b9d111d","last_reissued_at":"2026-07-05T10:04:19.421753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:19.421753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Chunchao Guo, Di Wang, Fan Yang, Hongxu Zhao, Huiwen Shi, Jiaao Yu, Jiacheng Wang, Jie Jiang, Jing Xu, Junta Wu, Lifu Wang, Qingxiang Lin, Shaoxiong Yang, Sicong Liu, Xianghui Yang, Xinhai Liu, Xinzhou Wang, Yihang Lian, Yong Yang, Yuhong Liu, Zebin He, Zhuo Chen","submitted_at":"2024-11-04T17:21:42Z","abstract_excerpt":"While 3D generative models have greatly improved artists' workflows, the existing diffusion models for 3D generation suffer from slow generation and poor generalization. To address this issue, we propose a two-stage approach named Hunyuan3D 1.0 including a lite version and a standard version, that both support text- and image-conditioned generation. In the first stage, we employ a multi-view diffusion model that efficiently generates multi-view RGB in approximately 4 seconds. These multi-view images capture rich details of the 3D asset from different viewpoints, relaxing the tasks from single-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02293","kind":"arxiv","version":5},"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/2411.02293/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":"2411.02293","created_at":"2026-07-05T10:04:19.421812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02293v5","created_at":"2026-07-05T10:04:19.421812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02293","created_at":"2026-07-05T10:04:19.421812+00:00"},{"alias_kind":"pith_short_12","alias_value":"S765KQREDPHM","created_at":"2026-07-05T10:04:19.421812+00:00"},{"alias_kind":"pith_short_16","alias_value":"S765KQREDPHMBE4C","created_at":"2026-07-05T10:04:19.421812+00:00"},{"alias_kind":"pith_short_8","alias_value":"S765KQRE","created_at":"2026-07-05T10:04:19.421812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06565","citing_title":"ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation","ref_index":98,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21938","citing_title":"Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08402","citing_title":"SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07012","citing_title":"Task Editing for Generalizable 3D Visuomotor Policy Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07971","citing_title":"DVD: Discrete Voxel Diffusion for 3D Generation and Editing","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31777","citing_title":"Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28060","citing_title":"ReScene: Structured Indoor Scene Reconstruction from Multi-View Captures","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2501.12202","citing_title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17853","citing_title":"CelloCut: Constructive Watertight Remeshing via Tetrahedral Cell Cuts","ref_index":41,"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":1,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15442","citing_title":"Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16504","citing_title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04349","citing_title":"VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image","ref_index":13,"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":46,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16624","citing_title":"SAM 3D: 3Dfy Anything in Images","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01743","citing_title":"MOC-3D: Manifold-Order Consistency for Text-to-3D Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07971","citing_title":"DVD: Discrete Voxel Diffusion for 3D Generation and Editing","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04707","citing_title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","ref_index":144,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S765KQREDPHMBE4CBRBWGGVQH6","json":"https://pith.science/pith/S765KQREDPHMBE4CBRBWGGVQH6.json","graph_json":"https://pith.science/api/pith-number/S765KQREDPHMBE4CBRBWGGVQH6/graph.json","events_json":"https://pith.science/api/pith-number/S765KQREDPHMBE4CBRBWGGVQH6/events.json","paper":"https://pith.science/paper/S765KQRE"},"agent_actions":{"view_html":"https://pith.science/pith/S765KQREDPHMBE4CBRBWGGVQH6","download_json":"https://pith.science/pith/S765KQREDPHMBE4CBRBWGGVQH6.json","view_paper":"https://pith.science/paper/S765KQRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02293&json=true","fetch_graph":"https://pith.science/api/pith-number/S765KQREDPHMBE4CBRBWGGVQH6/graph.json","fetch_events":"https://pith.science/api/pith-number/S765KQREDPHMBE4CBRBWGGVQH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S765KQREDPHMBE4CBRBWGGVQH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S765KQREDPHMBE4CBRBWGGVQH6/action/storage_attestation","attest_author":"https://pith.science/pith/S765KQREDPHMBE4CBRBWGGVQH6/action/author_attestation","sign_citation":"https://pith.science/pith/S765KQREDPHMBE4CBRBWGGVQH6/action/citation_signature","submit_replication":"https://pith.science/pith/S765KQREDPHMBE4CBRBWGGVQH6/action/replication_record"}},"created_at":"2026-07-05T10:04:19.421812+00:00","updated_at":"2026-07-05T10:04:19.421812+00:00"}