{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7UD7APV2FLVN2R6JQZCNID7LCQ","short_pith_number":"pith:7UD7APV2","schema_version":"1.0","canonical_sha256":"fd07f03eba2aeadd47c98644d40feb1417a5a09e929c37d69865df891e6c8c1d","source":{"kind":"arxiv","id":"2506.08004","version":1},"attestation_state":"computed","paper":{"title":"Dynamic View Synthesis as an Inverse Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hidir Yesiltepe, Pinar Yanardag","submitted_at":"2025-06-09T17:59:47Z","abstract_excerpt":"In this work, we address dynamic view synthesis from monocular videos as an inverse problem in a training-free setting. By redesigning the noise initialization phase of a pre-trained video diffusion model, we enable high-fidelity dynamic view synthesis without any weight updates or auxiliary modules. We begin by identifying a fundamental obstacle to deterministic inversion arising from zero-terminal signal-to-noise ratio (SNR) schedules and resolve it by introducing a novel noise representation, termed K-order Recursive Noise Representation. We derive a closed form expression for this represen"},"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":"2506.08004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5e32d3e4ecaf412b6bab82ad769e384f0804bdc1189cc3b11c8669629ecdb07d","abstract_canon_sha256":"ae810c0cc7bdc7af3279de1dd4a1ae6afa451c550efafe531e044b805d5fef69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:37.047568Z","signature_b64":"4888D64dUyqPKCEv7kH1uG1+8vWaZuZHcYcCRABY6rx6geBbcN+r0QSNpU73+/GgLKhAf0VjTxclqoeLFqBMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd07f03eba2aeadd47c98644d40feb1417a5a09e929c37d69865df891e6c8c1d","last_reissued_at":"2026-07-05T11:18:37.047130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:37.047130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic View Synthesis as an Inverse Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hidir Yesiltepe, Pinar Yanardag","submitted_at":"2025-06-09T17:59:47Z","abstract_excerpt":"In this work, we address dynamic view synthesis from monocular videos as an inverse problem in a training-free setting. By redesigning the noise initialization phase of a pre-trained video diffusion model, we enable high-fidelity dynamic view synthesis without any weight updates or auxiliary modules. We begin by identifying a fundamental obstacle to deterministic inversion arising from zero-terminal signal-to-noise ratio (SNR) schedules and resolve it by introducing a novel noise representation, termed K-order Recursive Noise Representation. We derive a closed form expression for this represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08004","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/2506.08004/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":"2506.08004","created_at":"2026-07-05T11:18:37.047185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08004v1","created_at":"2026-07-05T11:18:37.047185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08004","created_at":"2026-07-05T11:18:37.047185+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UD7APV2FLVN","created_at":"2026-07-05T11:18:37.047185+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UD7APV2FLVN2R6J","created_at":"2026-07-05T11:18:37.047185+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UD7APV2","created_at":"2026-07-05T11:18:37.047185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14988","citing_title":"Compositional Video Generation via Inference-Time Guidance","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30431","citing_title":"DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07209","citing_title":"INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling","ref_index":97,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UD7APV2FLVN2R6JQZCNID7LCQ","json":"https://pith.science/pith/7UD7APV2FLVN2R6JQZCNID7LCQ.json","graph_json":"https://pith.science/api/pith-number/7UD7APV2FLVN2R6JQZCNID7LCQ/graph.json","events_json":"https://pith.science/api/pith-number/7UD7APV2FLVN2R6JQZCNID7LCQ/events.json","paper":"https://pith.science/paper/7UD7APV2"},"agent_actions":{"view_html":"https://pith.science/pith/7UD7APV2FLVN2R6JQZCNID7LCQ","download_json":"https://pith.science/pith/7UD7APV2FLVN2R6JQZCNID7LCQ.json","view_paper":"https://pith.science/paper/7UD7APV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08004&json=true","fetch_graph":"https://pith.science/api/pith-number/7UD7APV2FLVN2R6JQZCNID7LCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7UD7APV2FLVN2R6JQZCNID7LCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UD7APV2FLVN2R6JQZCNID7LCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UD7APV2FLVN2R6JQZCNID7LCQ/action/storage_attestation","attest_author":"https://pith.science/pith/7UD7APV2FLVN2R6JQZCNID7LCQ/action/author_attestation","sign_citation":"https://pith.science/pith/7UD7APV2FLVN2R6JQZCNID7LCQ/action/citation_signature","submit_replication":"https://pith.science/pith/7UD7APV2FLVN2R6JQZCNID7LCQ/action/replication_record"}},"created_at":"2026-07-05T11:18:37.047185+00:00","updated_at":"2026-07-05T11:18:37.047185+00:00"}