{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:36CUHDLG4MIA5DJVZWO7KRVZ43","short_pith_number":"pith:36CUHDLG","schema_version":"1.0","canonical_sha256":"df85438d66e3100e8d35cd9df546b9e6fe30922cf15e1a10a86315932fdbb62f","source":{"kind":"arxiv","id":"2404.07199","version":2},"attestation_state":"computed","paper":{"title":"RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Trevithick, Jaidev Shriram, Lingjie Liu, Ravi Ramamoorthi","submitted_at":"2024-04-10T17:57:41Z","abstract_excerpt":"We introduce RealmDreamer, a technique for generating forward-facing 3D scenes from text descriptions. Our method optimizes a 3D Gaussian Splatting representation to match complex text prompts using pretrained diffusion models. Our key insight is to leverage 2D inpainting diffusion models conditioned on an initial scene estimate to provide low variance supervision for unknown regions during 3D distillation. In conjunction, we imbue high-fidelity geometry with geometric distillation from a depth diffusion model, conditioned on samples from the inpainting model. We find that the initialization o"},"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":"2404.07199","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T17:57:41Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"6e55a8949a18f8443dcb76aaac512634760842d4e37821cbcb8a1374b374be6f","abstract_canon_sha256":"c9820e886694db58edc19fbda52dbfff3815bfb59ae6d6d9a6f0b5a8ee132cd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:15.795249Z","signature_b64":"xgDLEtW2CxeExIFX4Yo7tNeHE+RqzOE9Ya8JDL5L6EeBI9MW2vCLHzzwuIcBnloPf0vBDHxEX24pKGUxX3EgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df85438d66e3100e8d35cd9df546b9e6fe30922cf15e1a10a86315932fdbb62f","last_reissued_at":"2026-07-05T10:28:15.794706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:15.794706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Trevithick, Jaidev Shriram, Lingjie Liu, Ravi Ramamoorthi","submitted_at":"2024-04-10T17:57:41Z","abstract_excerpt":"We introduce RealmDreamer, a technique for generating forward-facing 3D scenes from text descriptions. Our method optimizes a 3D Gaussian Splatting representation to match complex text prompts using pretrained diffusion models. Our key insight is to leverage 2D inpainting diffusion models conditioned on an initial scene estimate to provide low variance supervision for unknown regions during 3D distillation. In conjunction, we imbue high-fidelity geometry with geometric distillation from a depth diffusion model, conditioned on samples from the inpainting model. We find that the initialization o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07199","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/2404.07199/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":"2404.07199","created_at":"2026-07-05T10:28:15.794766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07199v2","created_at":"2026-07-05T10:28:15.794766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07199","created_at":"2026-07-05T10:28:15.794766+00:00"},{"alias_kind":"pith_short_12","alias_value":"36CUHDLG4MIA","created_at":"2026-07-05T10:28:15.794766+00:00"},{"alias_kind":"pith_short_16","alias_value":"36CUHDLG4MIA5DJV","created_at":"2026-07-05T10:28:15.794766+00:00"},{"alias_kind":"pith_short_8","alias_value":"36CUHDLG","created_at":"2026-07-05T10:28:15.794766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05392","citing_title":"SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25503","citing_title":"AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2411.14295","citing_title":"DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation","ref_index":32,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02048","citing_title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09414","citing_title":"Depth Anything V2","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13036","citing_title":"Lyra 2.0: Explorable Generative 3D Worlds","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09330","citing_title":"VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36CUHDLG4MIA5DJVZWO7KRVZ43","json":"https://pith.science/pith/36CUHDLG4MIA5DJVZWO7KRVZ43.json","graph_json":"https://pith.science/api/pith-number/36CUHDLG4MIA5DJVZWO7KRVZ43/graph.json","events_json":"https://pith.science/api/pith-number/36CUHDLG4MIA5DJVZWO7KRVZ43/events.json","paper":"https://pith.science/paper/36CUHDLG"},"agent_actions":{"view_html":"https://pith.science/pith/36CUHDLG4MIA5DJVZWO7KRVZ43","download_json":"https://pith.science/pith/36CUHDLG4MIA5DJVZWO7KRVZ43.json","view_paper":"https://pith.science/paper/36CUHDLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07199&json=true","fetch_graph":"https://pith.science/api/pith-number/36CUHDLG4MIA5DJVZWO7KRVZ43/graph.json","fetch_events":"https://pith.science/api/pith-number/36CUHDLG4MIA5DJVZWO7KRVZ43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36CUHDLG4MIA5DJVZWO7KRVZ43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36CUHDLG4MIA5DJVZWO7KRVZ43/action/storage_attestation","attest_author":"https://pith.science/pith/36CUHDLG4MIA5DJVZWO7KRVZ43/action/author_attestation","sign_citation":"https://pith.science/pith/36CUHDLG4MIA5DJVZWO7KRVZ43/action/citation_signature","submit_replication":"https://pith.science/pith/36CUHDLG4MIA5DJVZWO7KRVZ43/action/replication_record"}},"created_at":"2026-07-05T10:28:15.794766+00:00","updated_at":"2026-07-05T10:28:15.794766+00:00"}