{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4HZ4QH7IHORM65FZ7YEDGYATUY","short_pith_number":"pith:4HZ4QH7I","schema_version":"1.0","canonical_sha256":"e1f3c81fe83ba2cf74b9fe08336013a620fbbd9b51f59218ec99c53fcc9daf92","source":{"kind":"arxiv","id":"2502.14247","version":2},"attestation_state":"computed","paper":{"title":"Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Hongdong Li, Jiayu Yang, Pan Ji, Senbo Wang, Shenzhou Chen, Taizhang Shang, Weixuan Sun, Weizhe Liu, Xibin Song, Ziang Cheng","submitted_at":"2025-02-20T04:22:30Z","abstract_excerpt":"This report presents a comprehensive framework for generating high-quality 3D shapes and textures from diverse input prompts, including single images, multi-view images, and text descriptions. The framework consists of 3D shape generation and texture generation. (1). The 3D shape generation pipeline employs a Variational Autoencoder (VAE) to encode implicit 3D geometries into a latent space and a diffusion network to generate latents conditioned on input prompts, with modifications to enhance model capacity. An alternative Artist-Created Mesh (AM) generation approach is also explored, yielding"},"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":"2502.14247","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2025-02-20T04:22:30Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"a65f8ee7516a00f4f5cd0beae22db0e2543158fd63925150603ae4831b0eb828","abstract_canon_sha256":"a104764ecef9ffd357788d122d8005029aa172c9645242a56f2fd5d2ce673450"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:14.336664Z","signature_b64":"Gh2pEo8aes7jVlwCu4YjB7pfqESqoM77wyfBIyLFrDWlHhfiNQr9ICwcgelUu+gg4DCXuLpEdXs2hii4n9vsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1f3c81fe83ba2cf74b9fe08336013a620fbbd9b51f59218ec99c53fcc9daf92","last_reissued_at":"2026-07-05T10:18:14.336168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:14.336168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Hongdong Li, Jiayu Yang, Pan Ji, Senbo Wang, Shenzhou Chen, Taizhang Shang, Weixuan Sun, Weizhe Liu, Xibin Song, Ziang Cheng","submitted_at":"2025-02-20T04:22:30Z","abstract_excerpt":"This report presents a comprehensive framework for generating high-quality 3D shapes and textures from diverse input prompts, including single images, multi-view images, and text descriptions. The framework consists of 3D shape generation and texture generation. (1). The 3D shape generation pipeline employs a Variational Autoencoder (VAE) to encode implicit 3D geometries into a latent space and a diffusion network to generate latents conditioned on input prompts, with modifications to enhance model capacity. An alternative Artist-Created Mesh (AM) generation approach is also explored, yielding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14247","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/2502.14247/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":"2502.14247","created_at":"2026-07-05T10:18:14.336229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14247v2","created_at":"2026-07-05T10:18:14.336229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14247","created_at":"2026-07-05T10:18:14.336229+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HZ4QH7IHORM","created_at":"2026-07-05T10:18:14.336229+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HZ4QH7IHORM65FZ","created_at":"2026-07-05T10:18:14.336229+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HZ4QH7I","created_at":"2026-07-05T10:18:14.336229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07817","citing_title":"DreamCharacter-1: From 3D Generative Foundation Models to Product-Ready Character Generation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01222","citing_title":"Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14692","citing_title":"Native and Compact Structured Latents for 3D Generation","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22394","citing_title":"PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09231","citing_title":"Hitem3D 2.0: Multi-View Guided Native 3D Texture Generation","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HZ4QH7IHORM65FZ7YEDGYATUY","json":"https://pith.science/pith/4HZ4QH7IHORM65FZ7YEDGYATUY.json","graph_json":"https://pith.science/api/pith-number/4HZ4QH7IHORM65FZ7YEDGYATUY/graph.json","events_json":"https://pith.science/api/pith-number/4HZ4QH7IHORM65FZ7YEDGYATUY/events.json","paper":"https://pith.science/paper/4HZ4QH7I"},"agent_actions":{"view_html":"https://pith.science/pith/4HZ4QH7IHORM65FZ7YEDGYATUY","download_json":"https://pith.science/pith/4HZ4QH7IHORM65FZ7YEDGYATUY.json","view_paper":"https://pith.science/paper/4HZ4QH7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14247&json=true","fetch_graph":"https://pith.science/api/pith-number/4HZ4QH7IHORM65FZ7YEDGYATUY/graph.json","fetch_events":"https://pith.science/api/pith-number/4HZ4QH7IHORM65FZ7YEDGYATUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HZ4QH7IHORM65FZ7YEDGYATUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HZ4QH7IHORM65FZ7YEDGYATUY/action/storage_attestation","attest_author":"https://pith.science/pith/4HZ4QH7IHORM65FZ7YEDGYATUY/action/author_attestation","sign_citation":"https://pith.science/pith/4HZ4QH7IHORM65FZ7YEDGYATUY/action/citation_signature","submit_replication":"https://pith.science/pith/4HZ4QH7IHORM65FZ7YEDGYATUY/action/replication_record"}},"created_at":"2026-07-05T10:18:14.336229+00:00","updated_at":"2026-07-05T10:18:14.336229+00:00"}