{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KVZXKI2FDIPP7BC2HNMBYKUFPS","short_pith_number":"pith:KVZXKI2F","schema_version":"1.0","canonical_sha256":"55737523451a1eff845a3b581c2a857c8326879f10aea0cef3df83e74f3ec52c","source":{"kind":"arxiv","id":"2403.09981","version":3},"attestation_state":"computed","paper":{"title":"Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingzhe Zhao, Peidong Liu, Yiming Chen, Zhiqi Li","submitted_at":"2024-03-15T02:57:20Z","abstract_excerpt":"While text-to-3D and image-to-3D generation tasks have received considerable attention, one important but under-explored field between them is controllable text-to-3D generation, which we mainly focus on in this work. To address this task, 1) we introduce Multi-view ControlNet (MVControl), a novel neural network architecture designed to enhance existing pre-trained multi-view diffusion models by integrating additional input conditions, such as edge, depth, normal, and scribble maps. Our innovation lies in the introduction of a conditioning module that controls the base diffusion model using bo"},"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":"2403.09981","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T02:57:20Z","cross_cats_sorted":[],"title_canon_sha256":"f2fe38d9835639368fe51424e52126a1d4b0e46871aa5395a2fdd87789af8970","abstract_canon_sha256":"ac03ab92b5e721c215e2027e5a585b7defe508ed202ef523cfc7fa8a3cd3736d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:17.628550Z","signature_b64":"9080D9uP7mdfB4T+KbeAUoDC1MmmWxraEQpCAd3cCp2yVp2+OO6C5OA8FjIXYfTfn7JUF2ntA8ob1vKFzSTMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55737523451a1eff845a3b581c2a857c8326879f10aea0cef3df83e74f3ec52c","last_reissued_at":"2026-07-05T10:11:17.628036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:17.628036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingzhe Zhao, Peidong Liu, Yiming Chen, Zhiqi Li","submitted_at":"2024-03-15T02:57:20Z","abstract_excerpt":"While text-to-3D and image-to-3D generation tasks have received considerable attention, one important but under-explored field between them is controllable text-to-3D generation, which we mainly focus on in this work. To address this task, 1) we introduce Multi-view ControlNet (MVControl), a novel neural network architecture designed to enhance existing pre-trained multi-view diffusion models by integrating additional input conditions, such as edge, depth, normal, and scribble maps. Our innovation lies in the introduction of a conditioning module that controls the base diffusion model using bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09981","kind":"arxiv","version":3},"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/2403.09981/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":"2403.09981","created_at":"2026-07-05T10:11:17.628091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09981v3","created_at":"2026-07-05T10:11:17.628091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09981","created_at":"2026-07-05T10:11:17.628091+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVZXKI2FDIPP","created_at":"2026-07-05T10:11:17.628091+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVZXKI2FDIPP7BC2","created_at":"2026-07-05T10:11:17.628091+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVZXKI2F","created_at":"2026-07-05T10:11:17.628091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":202,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13036","citing_title":"Lyra 2.0: Explorable Generative 3D Worlds","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVZXKI2FDIPP7BC2HNMBYKUFPS","json":"https://pith.science/pith/KVZXKI2FDIPP7BC2HNMBYKUFPS.json","graph_json":"https://pith.science/api/pith-number/KVZXKI2FDIPP7BC2HNMBYKUFPS/graph.json","events_json":"https://pith.science/api/pith-number/KVZXKI2FDIPP7BC2HNMBYKUFPS/events.json","paper":"https://pith.science/paper/KVZXKI2F"},"agent_actions":{"view_html":"https://pith.science/pith/KVZXKI2FDIPP7BC2HNMBYKUFPS","download_json":"https://pith.science/pith/KVZXKI2FDIPP7BC2HNMBYKUFPS.json","view_paper":"https://pith.science/paper/KVZXKI2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09981&json=true","fetch_graph":"https://pith.science/api/pith-number/KVZXKI2FDIPP7BC2HNMBYKUFPS/graph.json","fetch_events":"https://pith.science/api/pith-number/KVZXKI2FDIPP7BC2HNMBYKUFPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVZXKI2FDIPP7BC2HNMBYKUFPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVZXKI2FDIPP7BC2HNMBYKUFPS/action/storage_attestation","attest_author":"https://pith.science/pith/KVZXKI2FDIPP7BC2HNMBYKUFPS/action/author_attestation","sign_citation":"https://pith.science/pith/KVZXKI2FDIPP7BC2HNMBYKUFPS/action/citation_signature","submit_replication":"https://pith.science/pith/KVZXKI2FDIPP7BC2HNMBYKUFPS/action/replication_record"}},"created_at":"2026-07-05T10:11:17.628091+00:00","updated_at":"2026-07-05T10:11:17.628091+00:00"}