{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7KNJP6BQXAABVMPD6JK2UXRY4I","short_pith_number":"pith:7KNJP6BQ","schema_version":"1.0","canonical_sha256":"fa9a97f830b8001ab1e3f255aa5e38e2364ef60c5015ee1aba33b47e8234d4c9","source":{"kind":"arxiv","id":"2505.11992","version":2},"attestation_state":"computed","paper":{"title":"SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqing Zou, Huiyao Xu, Hujun Bao, Sitong Guo, Songchun Zhang, Weiwei Xu, Zhongwei Xie","submitted_at":"2025-05-17T13:05:13Z","abstract_excerpt":"Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of reconstructing photorealistic 3D scenes from sparse or single-view inputs. We introduce SpatialCrafter, a framework that leverages the rich knowledge in video diffusion models to generate plausible additional observations, thereby alleviating reconstruction ambiguity. Through a trainable camera encoder and an epipolar attention mechanism for explicit geometric co"},"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":"2505.11992","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-17T13:05:13Z","cross_cats_sorted":[],"title_canon_sha256":"390f68ee20eed79e273b891b6cdfffc7f9e17374e736b6c39bacaacb22645056","abstract_canon_sha256":"e9b47a8c8c011e94e25d2b2e6b8337e574ab7ce0fec87d1058e15cfdc5b2eb2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:35.242487Z","signature_b64":"YebUV8NXvCSr5MmdXZzyVAVySssCGesnoHho37xddVMoDPMd/i7GYxfHDYm8eeTwMs5pRGqZMntjkkbDyulYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa9a97f830b8001ab1e3f255aa5e38e2364ef60c5015ee1aba33b47e8234d4c9","last_reissued_at":"2026-07-05T11:35:35.242006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:35.242006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqing Zou, Huiyao Xu, Hujun Bao, Sitong Guo, Songchun Zhang, Weiwei Xu, Zhongwei Xie","submitted_at":"2025-05-17T13:05:13Z","abstract_excerpt":"Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of reconstructing photorealistic 3D scenes from sparse or single-view inputs. We introduce SpatialCrafter, a framework that leverages the rich knowledge in video diffusion models to generate plausible additional observations, thereby alleviating reconstruction ambiguity. Through a trainable camera encoder and an epipolar attention mechanism for explicit geometric co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11992","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/2505.11992/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":"2505.11992","created_at":"2026-07-05T11:35:35.242060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11992v2","created_at":"2026-07-05T11:35:35.242060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11992","created_at":"2026-07-05T11:35:35.242060+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KNJP6BQXAAB","created_at":"2026-07-05T11:35:35.242060+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KNJP6BQXAABVMPD","created_at":"2026-07-05T11:35:35.242060+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KNJP6BQ","created_at":"2026-07-05T11:35:35.242060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13036","citing_title":"Lyra 2.0: Explorable Generative 3D Worlds","ref_index":136,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7KNJP6BQXAABVMPD6JK2UXRY4I","json":"https://pith.science/pith/7KNJP6BQXAABVMPD6JK2UXRY4I.json","graph_json":"https://pith.science/api/pith-number/7KNJP6BQXAABVMPD6JK2UXRY4I/graph.json","events_json":"https://pith.science/api/pith-number/7KNJP6BQXAABVMPD6JK2UXRY4I/events.json","paper":"https://pith.science/paper/7KNJP6BQ"},"agent_actions":{"view_html":"https://pith.science/pith/7KNJP6BQXAABVMPD6JK2UXRY4I","download_json":"https://pith.science/pith/7KNJP6BQXAABVMPD6JK2UXRY4I.json","view_paper":"https://pith.science/paper/7KNJP6BQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11992&json=true","fetch_graph":"https://pith.science/api/pith-number/7KNJP6BQXAABVMPD6JK2UXRY4I/graph.json","fetch_events":"https://pith.science/api/pith-number/7KNJP6BQXAABVMPD6JK2UXRY4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KNJP6BQXAABVMPD6JK2UXRY4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KNJP6BQXAABVMPD6JK2UXRY4I/action/storage_attestation","attest_author":"https://pith.science/pith/7KNJP6BQXAABVMPD6JK2UXRY4I/action/author_attestation","sign_citation":"https://pith.science/pith/7KNJP6BQXAABVMPD6JK2UXRY4I/action/citation_signature","submit_replication":"https://pith.science/pith/7KNJP6BQXAABVMPD6JK2UXRY4I/action/replication_record"}},"created_at":"2026-07-05T11:35:35.242060+00:00","updated_at":"2026-07-05T11:35:35.242060+00:00"}