{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OECOV2WWYT34CYK7BHDKKWGFGE","short_pith_number":"pith:OECOV2WW","schema_version":"1.0","canonical_sha256":"7104eaead6c4f7c1615f09c6a558c5310081cdf17f6ecbd7236e37c3bc7f2139","source":{"kind":"arxiv","id":"2305.16213","version":2},"attestation_state":"computed","paper":{"title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cheng Lu, Chongxuan Li, Fan Bao, Hang Su, Jun Zhu, Yikai Wang, Zhengyi Wang","submitted_at":"2023-05-25T16:19:18Z","abstract_excerpt":"Score distillation sampling (SDS) has shown great promise in text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models, but suffers from over-saturation, over-smoothing, and low-diversity problems. In this work, we propose to model the 3D parameter as a random variable instead of a constant as in SDS and present variational score distillation (VSD), a principled particle-based variational framework to explain and address the aforementioned issues in text-to-3D generation. We show that SDS is a special case of VSD and leads to poor samples with both small and lar"},"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":"2305.16213","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T16:19:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2baf4fa191a200e4eafe47d01db62e5758676173b126162aded6d59e37bb579d","abstract_canon_sha256":"dea9185c42989d5c0c9a8794b3af8f03d3023b2b59c7764e5e593b7c27f784f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:14.420360Z","signature_b64":"p7ryRhrsE0DrWXsIGH2fm0Bd5i4hiv5An6br0E58KjzR1/egWdYmKtZUvLZSv6NXI+tj2WgzXtrf7+hSnn76BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7104eaead6c4f7c1615f09c6a558c5310081cdf17f6ecbd7236e37c3bc7f2139","last_reissued_at":"2026-07-05T07:15:14.419856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:14.419856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cheng Lu, Chongxuan Li, Fan Bao, Hang Su, Jun Zhu, Yikai Wang, Zhengyi Wang","submitted_at":"2023-05-25T16:19:18Z","abstract_excerpt":"Score distillation sampling (SDS) has shown great promise in text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models, but suffers from over-saturation, over-smoothing, and low-diversity problems. In this work, we propose to model the 3D parameter as a random variable instead of a constant as in SDS and present variational score distillation (VSD), a principled particle-based variational framework to explain and address the aforementioned issues in text-to-3D generation. We show that SDS is a special case of VSD and leads to poor samples with both small and lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16213","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/2305.16213/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":"2305.16213","created_at":"2026-07-05T07:15:14.419917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16213v2","created_at":"2026-07-05T07:15:14.419917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16213","created_at":"2026-07-05T07:15:14.419917+00:00"},{"alias_kind":"pith_short_12","alias_value":"OECOV2WWYT34","created_at":"2026-07-05T07:15:14.419917+00:00"},{"alias_kind":"pith_short_16","alias_value":"OECOV2WWYT34CYK7","created_at":"2026-07-05T07:15:14.419917+00:00"},{"alias_kind":"pith_short_8","alias_value":"OECOV2WW","created_at":"2026-07-05T07:15:14.419917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06609","citing_title":"D2PO: Optimizing Diffusion Samplers via Dynamic Preference","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05392","citing_title":"SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22481","citing_title":"Lighting-Consistent Object Transfer Across Radiance Fields","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21982","citing_title":"CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01803","citing_title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12099","citing_title":"ISAP-3D: Identity-Slot Aligned Part-Aware 3D Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07117","citing_title":"Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00522","citing_title":"Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15055","citing_title":"DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32020","citing_title":"Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2312.16476","citing_title":"SVGDreamer: Text Guided SVG Generation with Diffusion Model","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2401.16764","citing_title":"BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":264,"is_internal_anchor":false},{"citing_arxiv_id":"2310.15110","citing_title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2408.14837","citing_title":"Diffusion Models Are Real-Time Game Engines","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03453","citing_title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16653","citing_title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2308.16512","citing_title":"MVDream: Multi-view Diffusion for 3D Generation","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27504","citing_title":"REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":181,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OECOV2WWYT34CYK7BHDKKWGFGE","json":"https://pith.science/pith/OECOV2WWYT34CYK7BHDKKWGFGE.json","graph_json":"https://pith.science/api/pith-number/OECOV2WWYT34CYK7BHDKKWGFGE/graph.json","events_json":"https://pith.science/api/pith-number/OECOV2WWYT34CYK7BHDKKWGFGE/events.json","paper":"https://pith.science/paper/OECOV2WW"},"agent_actions":{"view_html":"https://pith.science/pith/OECOV2WWYT34CYK7BHDKKWGFGE","download_json":"https://pith.science/pith/OECOV2WWYT34CYK7BHDKKWGFGE.json","view_paper":"https://pith.science/paper/OECOV2WW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16213&json=true","fetch_graph":"https://pith.science/api/pith-number/OECOV2WWYT34CYK7BHDKKWGFGE/graph.json","fetch_events":"https://pith.science/api/pith-number/OECOV2WWYT34CYK7BHDKKWGFGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OECOV2WWYT34CYK7BHDKKWGFGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OECOV2WWYT34CYK7BHDKKWGFGE/action/storage_attestation","attest_author":"https://pith.science/pith/OECOV2WWYT34CYK7BHDKKWGFGE/action/author_attestation","sign_citation":"https://pith.science/pith/OECOV2WWYT34CYK7BHDKKWGFGE/action/citation_signature","submit_replication":"https://pith.science/pith/OECOV2WWYT34CYK7BHDKKWGFGE/action/replication_record"}},"created_at":"2026-07-05T07:15:14.419917+00:00","updated_at":"2026-07-05T07:15:14.419917+00:00"}