{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PLUUODBCGHELA7TEQLA54273DN","short_pith_number":"pith:PLUUODBC","schema_version":"1.0","canonical_sha256":"7ae9470c2231c8b07e6482c1de6bfb1b7859c17f6a18bf49f43a968811250699","source":{"kind":"arxiv","id":"2601.00678","version":3},"attestation_state":"computed","paper":{"title":"Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single image generates camera-controlled 4D video by building dynamic 3D Gaussians in one forward pass.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniela Ivanova, John H. Williamson, Melonie de Almeida, Paul Henderson, Tong Shi","submitted_at":"2026-01-02T13:04:47Z","abstract_excerpt":"Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent systems. Recent approaches have improved temporal coherence and 3D consistency in single-image-conditioned video generation. However, these methods often lack robust user controllability, such as modifying the camera path, limiting their applicability in real-world applications. Most existing camera-controlled image-to-video models struggle with accurately modeling camera motion, maintaining temporal consistency, an"},"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":true},"canonical_record":{"source":{"id":"2601.00678","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-02T13:04:47Z","cross_cats_sorted":[],"title_canon_sha256":"789eb2a1883f0da3ab46aaba103240bbbfa168317bce27c19311ca0d7ac6d501","abstract_canon_sha256":"833c824125563742c2f1d223bd211edee8283e01eed3677f28d2ba00f13e2346"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:31.598471Z","signature_b64":"x/D/awwKgQy11mbe5nrrTyCCyWWNi+4g0W4i/w3qnjt0PwDj/eipMULhArhEMwjhd5em5i3VxxB6Omh3rs8yBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ae9470c2231c8b07e6482c1de6bfb1b7859c17f6a18bf49f43a968811250699","last_reissued_at":"2026-05-20T00:00:31.597676Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:31.597676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single image generates camera-controlled 4D video by building dynamic 3D Gaussians in one forward pass.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniela Ivanova, John H. Williamson, Melonie de Almeida, Paul Henderson, Tong Shi","submitted_at":"2026-01-02T13:04:47Z","abstract_excerpt":"Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent systems. Recent approaches have improved temporal coherence and 3D consistency in single-image-conditioned video generation. However, these methods often lack robust user controllability, such as modifying the camera path, limiting their applicability in real-world applications. Most existing camera-controlled image-to-video models struggle with accurately modeling camera motion, maintaining temporal consistency, an"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose a novel framework that constructs a 3D Gaussian scene representation and samples plausible object motion, given a single image in a single forward pass. This enables fast, camera-guided video generation without the need for iterative denoising to inject object motion into render frames.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a single static image contains enough information to construct an accurate 3D Gaussian representation and to sample plausible, temporally consistent object motions that align with an arbitrary camera trajectory.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A unified single-pass framework using dynamic 3D Gaussians generates temporally consistent camera-controlled videos from a single image.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single image generates camera-controlled 4D video by building dynamic 3D Gaussians in one forward pass.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"024267b2deef697a55d825b93499a445927c43dbc65c677cf09bd9159cf5ec07"},"source":{"id":"2601.00678","kind":"arxiv","version":3},"verdict":{"id":"3a99a645-2cc1-4cb4-81cd-e05d2bc3844d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T18:16:01.870709Z","strongest_claim":"We propose a novel framework that constructs a 3D Gaussian scene representation and samples plausible object motion, given a single image in a single forward pass. This enables fast, camera-guided video generation without the need for iterative denoising to inject object motion into render frames.","one_line_summary":"A unified single-pass framework using dynamic 3D Gaussians generates temporally consistent camera-controlled videos from a single image.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a single static image contains enough information to construct an accurate 3D Gaussian representation and to sample plausible, temporally consistent object motions that align with an arbitrary camera trajectory.","pith_extraction_headline":"A single image generates camera-controlled 4D video by building dynamic 3D Gaussians in one forward pass."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.00678/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":2,"snapshot_sha256":"203fea5536753bc95fa3d789080eabf1b6a2a225a4d6a209c5c3dffd008f6d29"},"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":"2601.00678","created_at":"2026-05-20T00:00:31.597799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.00678v3","created_at":"2026-05-20T00:00:31.597799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.00678","created_at":"2026-05-20T00:00:31.597799+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLUUODBCGHEL","created_at":"2026-05-20T00:00:31.597799+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLUUODBCGHELA7TE","created_at":"2026-05-20T00:00:31.597799+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLUUODBC","created_at":"2026-05-20T00:00:31.597799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":128,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PLUUODBCGHELA7TEQLA54273DN","json":"https://pith.science/pith/PLUUODBCGHELA7TEQLA54273DN.json","graph_json":"https://pith.science/api/pith-number/PLUUODBCGHELA7TEQLA54273DN/graph.json","events_json":"https://pith.science/api/pith-number/PLUUODBCGHELA7TEQLA54273DN/events.json","paper":"https://pith.science/paper/PLUUODBC"},"agent_actions":{"view_html":"https://pith.science/pith/PLUUODBCGHELA7TEQLA54273DN","download_json":"https://pith.science/pith/PLUUODBCGHELA7TEQLA54273DN.json","view_paper":"https://pith.science/paper/PLUUODBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.00678&json=true","fetch_graph":"https://pith.science/api/pith-number/PLUUODBCGHELA7TEQLA54273DN/graph.json","fetch_events":"https://pith.science/api/pith-number/PLUUODBCGHELA7TEQLA54273DN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLUUODBCGHELA7TEQLA54273DN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLUUODBCGHELA7TEQLA54273DN/action/storage_attestation","attest_author":"https://pith.science/pith/PLUUODBCGHELA7TEQLA54273DN/action/author_attestation","sign_citation":"https://pith.science/pith/PLUUODBCGHELA7TEQLA54273DN/action/citation_signature","submit_replication":"https://pith.science/pith/PLUUODBCGHELA7TEQLA54273DN/action/replication_record"}},"created_at":"2026-05-20T00:00:31.597799+00:00","updated_at":"2026-05-20T00:00:31.597799+00:00"}