{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:37RCG3TJG76NMXYMELCNA4WAFA","short_pith_number":"pith:37RCG3TJ","schema_version":"1.0","canonical_sha256":"dfe2236e6937fcd65f0c22c4d072c028142d884998470cad99038eeb084b78cb","source":{"kind":"arxiv","id":"2404.03575","version":2},"attestation_state":"computed","paper":{"title":"DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haolin Shi, Haoran Li, Lik-Hang Lee, Lin Wang, Pengyuan Zhou, Wenjun Wu, Wenli Zhang, Yong Liao","submitted_at":"2024-04-04T16:38:57Z","abstract_excerpt":"Text-to-3D scene generation holds immense potential for the gaming, film, and architecture sectors. Despite significant progress, existing methods struggle with maintaining high quality, consistency, and editing flexibility. In this paper, we propose DreamScene, a 3D Gaussian-based novel text-to-3D scene generation framework, to tackle the aforementioned three challenges mainly via two strategies. First, DreamScene employs Formation Pattern Sampling (FPS), a multi-timestep sampling strategy guided by the formation patterns of 3D objects, to form fast, semantically rich, and high-quality repres"},"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":"2404.03575","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T16:38:57Z","cross_cats_sorted":[],"title_canon_sha256":"4c535dfbe5242ade58378c78195fad972a878f074030eff5b3552218695fb9b2","abstract_canon_sha256":"77007e33a9d4f2b12e37c6d9f78c942155e014453474b24a3daa22704659c45b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:50.819840Z","signature_b64":"KmgS0bs9YVzj3DMjuuWodtN/3jIMS1i0lwnz4kc3gitcy4BqGBZhrl5ERQg9RSqnyoN8aPfh5bB/7ZXqh8FmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfe2236e6937fcd65f0c22c4d072c028142d884998470cad99038eeb084b78cb","last_reissued_at":"2026-07-05T08:45:50.819401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:50.819401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haolin Shi, Haoran Li, Lik-Hang Lee, Lin Wang, Pengyuan Zhou, Wenjun Wu, Wenli Zhang, Yong Liao","submitted_at":"2024-04-04T16:38:57Z","abstract_excerpt":"Text-to-3D scene generation holds immense potential for the gaming, film, and architecture sectors. Despite significant progress, existing methods struggle with maintaining high quality, consistency, and editing flexibility. In this paper, we propose DreamScene, a 3D Gaussian-based novel text-to-3D scene generation framework, to tackle the aforementioned three challenges mainly via two strategies. First, DreamScene employs Formation Pattern Sampling (FPS), a multi-timestep sampling strategy guided by the formation patterns of 3D objects, to form fast, semantically rich, and high-quality repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03575","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/2404.03575/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":"2404.03575","created_at":"2026-07-05T08:45:50.819461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03575v2","created_at":"2026-07-05T08:45:50.819461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03575","created_at":"2026-07-05T08:45:50.819461+00:00"},{"alias_kind":"pith_short_12","alias_value":"37RCG3TJG76N","created_at":"2026-07-05T08:45:50.819461+00:00"},{"alias_kind":"pith_short_16","alias_value":"37RCG3TJG76NMXYM","created_at":"2026-07-05T08:45:50.819461+00:00"},{"alias_kind":"pith_short_8","alias_value":"37RCG3TJ","created_at":"2026-07-05T08:45:50.819461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16807","citing_title":"DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37RCG3TJG76NMXYMELCNA4WAFA","json":"https://pith.science/pith/37RCG3TJG76NMXYMELCNA4WAFA.json","graph_json":"https://pith.science/api/pith-number/37RCG3TJG76NMXYMELCNA4WAFA/graph.json","events_json":"https://pith.science/api/pith-number/37RCG3TJG76NMXYMELCNA4WAFA/events.json","paper":"https://pith.science/paper/37RCG3TJ"},"agent_actions":{"view_html":"https://pith.science/pith/37RCG3TJG76NMXYMELCNA4WAFA","download_json":"https://pith.science/pith/37RCG3TJG76NMXYMELCNA4WAFA.json","view_paper":"https://pith.science/paper/37RCG3TJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03575&json=true","fetch_graph":"https://pith.science/api/pith-number/37RCG3TJG76NMXYMELCNA4WAFA/graph.json","fetch_events":"https://pith.science/api/pith-number/37RCG3TJG76NMXYMELCNA4WAFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37RCG3TJG76NMXYMELCNA4WAFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37RCG3TJG76NMXYMELCNA4WAFA/action/storage_attestation","attest_author":"https://pith.science/pith/37RCG3TJG76NMXYMELCNA4WAFA/action/author_attestation","sign_citation":"https://pith.science/pith/37RCG3TJG76NMXYMELCNA4WAFA/action/citation_signature","submit_replication":"https://pith.science/pith/37RCG3TJG76NMXYMELCNA4WAFA/action/replication_record"}},"created_at":"2026-07-05T08:45:50.819461+00:00","updated_at":"2026-07-05T08:45:50.819461+00:00"}