{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HPCLQW52E7ILOMSCUQXGM5I3FS","short_pith_number":"pith:HPCLQW52","schema_version":"1.0","canonical_sha256":"3bc4b85bba27d0b73242a42e66751b2ca1872444122356ebfc11a6f2c95e5bac","source":{"kind":"arxiv","id":"2503.16611","version":1},"attestation_state":"computed","paper":{"title":"A Recipe for Generating 3D Worlds From a Single Image","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Denys Rozumnyi, Katja Schwarz, Lorenzo Porzi, Peter Kontschieder, Samuel Rota Bul\\`o","submitted_at":"2025-03-20T18:06:12Z","abstract_excerpt":"We introduce a recipe for generating immersive 3D worlds from a single image by framing the task as an in-context learning problem for 2D inpainting models. This approach requires minimal training and uses existing generative models. Our process involves two steps: generating coherent panoramas using a pre-trained diffusion model and lifting these into 3D with a metric depth estimator. We then fill unobserved regions by conditioning the inpainting model on rendered point clouds, requiring minimal fine-tuning. Tested on both synthetic and real images, our method produces high-quality 3D environ"},"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":"2503.16611","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T18:06:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"45c2392e517d17729219e9554ba990c7c3deb877dee2da84a1f51c6a7f3c6997","abstract_canon_sha256":"9d8d81f2c6f722d407dd8088512ef3b657ad31a98c06d62e7d6ce856ebe94b78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:45.554271Z","signature_b64":"FX38u2nfeH020qc8zwLo3PDpPhK8cVm8g/ENumfDpAaIP+rGAT0DOBelDCHD7c+MQGrr4QA/hynYs6u5EovLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bc4b85bba27d0b73242a42e66751b2ca1872444122356ebfc11a6f2c95e5bac","last_reissued_at":"2026-07-05T10:36:45.553595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:45.553595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Recipe for Generating 3D Worlds From a Single Image","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Denys Rozumnyi, Katja Schwarz, Lorenzo Porzi, Peter Kontschieder, Samuel Rota Bul\\`o","submitted_at":"2025-03-20T18:06:12Z","abstract_excerpt":"We introduce a recipe for generating immersive 3D worlds from a single image by framing the task as an in-context learning problem for 2D inpainting models. This approach requires minimal training and uses existing generative models. Our process involves two steps: generating coherent panoramas using a pre-trained diffusion model and lifting these into 3D with a metric depth estimator. We then fill unobserved regions by conditioning the inpainting model on rendered point clouds, requiring minimal fine-tuning. Tested on both synthetic and real images, our method produces high-quality 3D environ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16611","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/2503.16611/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":"2503.16611","created_at":"2026-07-05T10:36:45.553678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16611v1","created_at":"2026-07-05T10:36:45.553678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16611","created_at":"2026-07-05T10:36:45.553678+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPCLQW52E7IL","created_at":"2026-07-05T10:36:45.553678+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPCLQW52E7ILOMSC","created_at":"2026-07-05T10:36:45.553678+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPCLQW52","created_at":"2026-07-05T10:36:45.553678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21809","citing_title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPCLQW52E7ILOMSCUQXGM5I3FS","json":"https://pith.science/pith/HPCLQW52E7ILOMSCUQXGM5I3FS.json","graph_json":"https://pith.science/api/pith-number/HPCLQW52E7ILOMSCUQXGM5I3FS/graph.json","events_json":"https://pith.science/api/pith-number/HPCLQW52E7ILOMSCUQXGM5I3FS/events.json","paper":"https://pith.science/paper/HPCLQW52"},"agent_actions":{"view_html":"https://pith.science/pith/HPCLQW52E7ILOMSCUQXGM5I3FS","download_json":"https://pith.science/pith/HPCLQW52E7ILOMSCUQXGM5I3FS.json","view_paper":"https://pith.science/paper/HPCLQW52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16611&json=true","fetch_graph":"https://pith.science/api/pith-number/HPCLQW52E7ILOMSCUQXGM5I3FS/graph.json","fetch_events":"https://pith.science/api/pith-number/HPCLQW52E7ILOMSCUQXGM5I3FS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPCLQW52E7ILOMSCUQXGM5I3FS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPCLQW52E7ILOMSCUQXGM5I3FS/action/storage_attestation","attest_author":"https://pith.science/pith/HPCLQW52E7ILOMSCUQXGM5I3FS/action/author_attestation","sign_citation":"https://pith.science/pith/HPCLQW52E7ILOMSCUQXGM5I3FS/action/citation_signature","submit_replication":"https://pith.science/pith/HPCLQW52E7ILOMSCUQXGM5I3FS/action/replication_record"}},"created_at":"2026-07-05T10:36:45.553678+00:00","updated_at":"2026-07-05T10:36:45.553678+00:00"}