{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:524ZXOZY7XWSI4P2K7V7IKZXO2","short_pith_number":"pith:524ZXOZY","schema_version":"1.0","canonical_sha256":"eeb99bbb38fded2471fa57ebf42b3776b51b6f51bb34e5783264d13aa1af519f","source":{"kind":"arxiv","id":"2501.05427","version":1},"attestation_state":"computed","paper":{"title":"Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wang, Jiahui Lei, Jiatao Gu, Kostas Daniilidis, Lingjie Liu, Xuyi Meng","submitted_at":"2025-01-09T18:37:35Z","abstract_excerpt":"Recent advances in 2D image generation have achieved remarkable quality,largely driven by the capacity of diffusion models and the availability of large-scale datasets. However, direct 3D generation is still constrained by the scarcity and lower fidelity of 3D datasets. In this paper, we introduce Zero-1-to-G, a novel approach that addresses this problem by enabling direct single-view generation on Gaussian splats using pretrained 2D diffusion models. Our key insight is that Gaussian splats, a 3D representation, can be decomposed into multi-view images encoding different attributes. This refra"},"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":"2501.05427","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:37:35Z","cross_cats_sorted":[],"title_canon_sha256":"85e1b0ed90044b8e45a481db063d06d693560591977a7b875558b223f0b406ed","abstract_canon_sha256":"99acf232a5e4ebedbce3382c25c43621272992510171ef0313d766d6efd35a53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:09.824534Z","signature_b64":"Fo2Sj8P5tJK2jgSDIxWcVhoGHX/bgvvSd9YTVIS4Qa5tCQFjRPXWDDq3yq+kXGGPSwzXWB5mksF8ItLdvB4JDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeb99bbb38fded2471fa57ebf42b3776b51b6f51bb34e5783264d13aa1af519f","last_reissued_at":"2026-07-05T09:59:09.824044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:09.824044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wang, Jiahui Lei, Jiatao Gu, Kostas Daniilidis, Lingjie Liu, Xuyi Meng","submitted_at":"2025-01-09T18:37:35Z","abstract_excerpt":"Recent advances in 2D image generation have achieved remarkable quality,largely driven by the capacity of diffusion models and the availability of large-scale datasets. However, direct 3D generation is still constrained by the scarcity and lower fidelity of 3D datasets. In this paper, we introduce Zero-1-to-G, a novel approach that addresses this problem by enabling direct single-view generation on Gaussian splats using pretrained 2D diffusion models. Our key insight is that Gaussian splats, a 3D representation, can be decomposed into multi-view images encoding different attributes. This refra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05427","kind":"arxiv","version":1},"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/2501.05427/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":"2501.05427","created_at":"2026-07-05T09:59:09.824100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05427v1","created_at":"2026-07-05T09:59:09.824100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05427","created_at":"2026-07-05T09:59:09.824100+00:00"},{"alias_kind":"pith_short_12","alias_value":"524ZXOZY7XWS","created_at":"2026-07-05T09:59:09.824100+00:00"},{"alias_kind":"pith_short_16","alias_value":"524ZXOZY7XWSI4P2","created_at":"2026-07-05T09:59:09.824100+00:00"},{"alias_kind":"pith_short_8","alias_value":"524ZXOZY","created_at":"2026-07-05T09:59:09.824100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01803","citing_title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29496","citing_title":"Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/524ZXOZY7XWSI4P2K7V7IKZXO2","json":"https://pith.science/pith/524ZXOZY7XWSI4P2K7V7IKZXO2.json","graph_json":"https://pith.science/api/pith-number/524ZXOZY7XWSI4P2K7V7IKZXO2/graph.json","events_json":"https://pith.science/api/pith-number/524ZXOZY7XWSI4P2K7V7IKZXO2/events.json","paper":"https://pith.science/paper/524ZXOZY"},"agent_actions":{"view_html":"https://pith.science/pith/524ZXOZY7XWSI4P2K7V7IKZXO2","download_json":"https://pith.science/pith/524ZXOZY7XWSI4P2K7V7IKZXO2.json","view_paper":"https://pith.science/paper/524ZXOZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05427&json=true","fetch_graph":"https://pith.science/api/pith-number/524ZXOZY7XWSI4P2K7V7IKZXO2/graph.json","fetch_events":"https://pith.science/api/pith-number/524ZXOZY7XWSI4P2K7V7IKZXO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/524ZXOZY7XWSI4P2K7V7IKZXO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/524ZXOZY7XWSI4P2K7V7IKZXO2/action/storage_attestation","attest_author":"https://pith.science/pith/524ZXOZY7XWSI4P2K7V7IKZXO2/action/author_attestation","sign_citation":"https://pith.science/pith/524ZXOZY7XWSI4P2K7V7IKZXO2/action/citation_signature","submit_replication":"https://pith.science/pith/524ZXOZY7XWSI4P2K7V7IKZXO2/action/replication_record"}},"created_at":"2026-07-05T09:59:09.824100+00:00","updated_at":"2026-07-05T09:59:09.824100+00:00"}