{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MI2HMRBX37TGVJTLOFMNLHPYCD","short_pith_number":"pith:MI2HMRBX","schema_version":"1.0","canonical_sha256":"6234764437dfe66aa66b7158d59df810e27ae775dcdb69bebaad1fb78894ff58","source":{"kind":"arxiv","id":"2501.05445","version":1},"attestation_state":"computed","paper":{"title":"Consistent Flow Distillation for Text-to-3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Runjie Yan, Xiaolong Wang, Yinbo Chen","submitted_at":"2025-01-09T18:56:05Z","abstract_excerpt":"Score Distillation Sampling (SDS) has made significant strides in distilling image-generative models for 3D generation. However, its maximum-likelihood-seeking behavior often leads to degraded visual quality and diversity, limiting its effectiveness in 3D applications. In this work, we propose Consistent Flow Distillation (CFD), which addresses these limitations. We begin by leveraging the gradient of the diffusion ODE or SDE sampling process to guide the 3D generation. From the gradient-based sampling perspective, we find that the consistency of 2D image flows across different viewpoints is i"},"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":"2501.05445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:56:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0917ff1340f7162209ccb523182f6138803f1de1606ebda7c729a78871d44153","abstract_canon_sha256":"10d4d20a86ec243febcce262632a230f38f5b3a488a6f707480b21d30dbdef28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:10.030987Z","signature_b64":"hNwnay5OdrKNd8WTAKQJozvqhGGIBaxSituYbqbeWyhdpI1KqMiAnW8+RKbpdmgmmcCgNkNfKss1SwniKKtEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6234764437dfe66aa66b7158d59df810e27ae775dcdb69bebaad1fb78894ff58","last_reissued_at":"2026-07-05T09:59:10.030499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:10.030499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistent Flow Distillation for Text-to-3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Runjie Yan, Xiaolong Wang, Yinbo Chen","submitted_at":"2025-01-09T18:56:05Z","abstract_excerpt":"Score Distillation Sampling (SDS) has made significant strides in distilling image-generative models for 3D generation. However, its maximum-likelihood-seeking behavior often leads to degraded visual quality and diversity, limiting its effectiveness in 3D applications. In this work, we propose Consistent Flow Distillation (CFD), which addresses these limitations. We begin by leveraging the gradient of the diffusion ODE or SDE sampling process to guide the 3D generation. From the gradient-based sampling perspective, we find that the consistency of 2D image flows across different viewpoints is i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05445","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/2501.05445/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":"2501.05445","created_at":"2026-07-05T09:59:10.030560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05445v1","created_at":"2026-07-05T09:59:10.030560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05445","created_at":"2026-07-05T09:59:10.030560+00:00"},{"alias_kind":"pith_short_12","alias_value":"MI2HMRBX37TG","created_at":"2026-07-05T09:59:10.030560+00:00"},{"alias_kind":"pith_short_16","alias_value":"MI2HMRBX37TGVJTL","created_at":"2026-07-05T09:59:10.030560+00:00"},{"alias_kind":"pith_short_8","alias_value":"MI2HMRBX","created_at":"2026-07-05T09:59:10.030560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20872","citing_title":"CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16355","citing_title":"Generative 3D Gaussians with Learned Density Control","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MI2HMRBX37TGVJTLOFMNLHPYCD","json":"https://pith.science/pith/MI2HMRBX37TGVJTLOFMNLHPYCD.json","graph_json":"https://pith.science/api/pith-number/MI2HMRBX37TGVJTLOFMNLHPYCD/graph.json","events_json":"https://pith.science/api/pith-number/MI2HMRBX37TGVJTLOFMNLHPYCD/events.json","paper":"https://pith.science/paper/MI2HMRBX"},"agent_actions":{"view_html":"https://pith.science/pith/MI2HMRBX37TGVJTLOFMNLHPYCD","download_json":"https://pith.science/pith/MI2HMRBX37TGVJTLOFMNLHPYCD.json","view_paper":"https://pith.science/paper/MI2HMRBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05445&json=true","fetch_graph":"https://pith.science/api/pith-number/MI2HMRBX37TGVJTLOFMNLHPYCD/graph.json","fetch_events":"https://pith.science/api/pith-number/MI2HMRBX37TGVJTLOFMNLHPYCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MI2HMRBX37TGVJTLOFMNLHPYCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MI2HMRBX37TGVJTLOFMNLHPYCD/action/storage_attestation","attest_author":"https://pith.science/pith/MI2HMRBX37TGVJTLOFMNLHPYCD/action/author_attestation","sign_citation":"https://pith.science/pith/MI2HMRBX37TGVJTLOFMNLHPYCD/action/citation_signature","submit_replication":"https://pith.science/pith/MI2HMRBX37TGVJTLOFMNLHPYCD/action/replication_record"}},"created_at":"2026-07-05T09:59:10.030560+00:00","updated_at":"2026-07-05T09:59:10.030560+00:00"}