{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IQGMNHWPF4AAS3NZT2V6X3LC6T","short_pith_number":"pith:IQGMNHWP","schema_version":"1.0","canonical_sha256":"440cc69ecf2f00096db99eabebed62f4c042ec3c2851762bfd74218572991785","source":{"kind":"arxiv","id":"2405.15364","version":2},"attestation_state":"computed","paper":{"title":"NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Liu, Junhui Hou, Meng You, Zhiyu Zhu","submitted_at":"2024-05-24T08:56:19Z","abstract_excerpt":"By harnessing the potent generative capabilities of pre-trained large video diffusion models, we propose NVS-Solver, a new novel view synthesis (NVS) paradigm that operates \\textit{without} the need for training. NVS-Solver adaptively modulates the diffusion sampling process with the given views to enable the creation of remarkable visual experiences from single or multiple views of static scenes or monocular videos of dynamic scenes. Specifically, built upon our theoretical modeling, we iteratively modulate the score function with the given scene priors represented with warped input views to "},"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":"2405.15364","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T08:56:19Z","cross_cats_sorted":[],"title_canon_sha256":"c99465e7519d08619549bfe1205d60b191c9c7fe584b04118ff1ef897019b111","abstract_canon_sha256":"6c6752811a6d87b45677d88706e58369d3f76547ee421bc1fe08cc15de924780"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:58.820392Z","signature_b64":"4tb8yILzuu5zm0Y4y0YQUEVMvjIUeV8iBzAxdODINpLnI7hxsOWTwBztB5ZX3jcHJB75DO+ONzHzg19iFsZ0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"440cc69ecf2f00096db99eabebed62f4c042ec3c2851762bfd74218572991785","last_reissued_at":"2026-07-05T10:42:58.819843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:58.819843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Liu, Junhui Hou, Meng You, Zhiyu Zhu","submitted_at":"2024-05-24T08:56:19Z","abstract_excerpt":"By harnessing the potent generative capabilities of pre-trained large video diffusion models, we propose NVS-Solver, a new novel view synthesis (NVS) paradigm that operates \\textit{without} the need for training. NVS-Solver adaptively modulates the diffusion sampling process with the given views to enable the creation of remarkable visual experiences from single or multiple views of static scenes or monocular videos of dynamic scenes. Specifically, built upon our theoretical modeling, we iteratively modulate the score function with the given scene priors represented with warped input views to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15364","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/2405.15364/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":"2405.15364","created_at":"2026-07-05T10:42:58.819916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15364v2","created_at":"2026-07-05T10:42:58.819916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15364","created_at":"2026-07-05T10:42:58.819916+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQGMNHWPF4AA","created_at":"2026-07-05T10:42:58.819916+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQGMNHWPF4AAS3NZ","created_at":"2026-07-05T10:42:58.819916+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQGMNHWP","created_at":"2026-07-05T10:42:58.819916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22835","citing_title":"OrthoMotion:Disentangling Camera and Subject Motion via Geometry Semantics Orthogonal Attention","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19805","citing_title":"ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14815","citing_title":"Probing into Camera Control of Video Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00299","citing_title":"Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18754","citing_title":"Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15182","citing_title":"Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12119","citing_title":"MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12119","citing_title":"MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21776","citing_title":"Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQGMNHWPF4AAS3NZT2V6X3LC6T","json":"https://pith.science/pith/IQGMNHWPF4AAS3NZT2V6X3LC6T.json","graph_json":"https://pith.science/api/pith-number/IQGMNHWPF4AAS3NZT2V6X3LC6T/graph.json","events_json":"https://pith.science/api/pith-number/IQGMNHWPF4AAS3NZT2V6X3LC6T/events.json","paper":"https://pith.science/paper/IQGMNHWP"},"agent_actions":{"view_html":"https://pith.science/pith/IQGMNHWPF4AAS3NZT2V6X3LC6T","download_json":"https://pith.science/pith/IQGMNHWPF4AAS3NZT2V6X3LC6T.json","view_paper":"https://pith.science/paper/IQGMNHWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15364&json=true","fetch_graph":"https://pith.science/api/pith-number/IQGMNHWPF4AAS3NZT2V6X3LC6T/graph.json","fetch_events":"https://pith.science/api/pith-number/IQGMNHWPF4AAS3NZT2V6X3LC6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQGMNHWPF4AAS3NZT2V6X3LC6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQGMNHWPF4AAS3NZT2V6X3LC6T/action/storage_attestation","attest_author":"https://pith.science/pith/IQGMNHWPF4AAS3NZT2V6X3LC6T/action/author_attestation","sign_citation":"https://pith.science/pith/IQGMNHWPF4AAS3NZT2V6X3LC6T/action/citation_signature","submit_replication":"https://pith.science/pith/IQGMNHWPF4AAS3NZT2V6X3LC6T/action/replication_record"}},"created_at":"2026-07-05T10:42:58.819916+00:00","updated_at":"2026-07-05T10:42:58.819916+00:00"}