{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SC4LSGB3NNFH3MY6W2KJREY2SH","short_pith_number":"pith:SC4LSGB3","schema_version":"1.0","canonical_sha256":"90b8b9183b6b4a7db31eb69498931a91e05e4d7581aa09a08f909f1b5231cb0d","source":{"kind":"arxiv","id":"2605.06280","version":4},"attestation_state":"computed","paper":{"title":"Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Adjacent-frame Eulerian motion fields with bidirectional cycle checks guide diffusion-based image animation without drift accumulation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyan Miao, Cong-Duy Nguyen, Khoi M. Le, Luu Anh Tuan, See-kiong Ng, Thong Nguyen","submitted_at":"2026-05-07T13:53:31Z","abstract_excerpt":"Recent advancements in image animation have utilized diffusion models to breathe life into static images. However, existing controllable frameworks typically rely on Lagrangian motion guidance, where optical flow is estimated relative to the initial frame. This paper revisits the same optical-flow primitive through a more local supervision design: we use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop. This shift enables parallelized training and provides bounded-error supervision throughout the generation process. To mit"},"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":"2605.06280","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-07T13:53:31Z","cross_cats_sorted":[],"title_canon_sha256":"9278ee30fae543d36b1bbef190c81641752d6592d0e13551b4250eeb3b0e1307","abstract_canon_sha256":"ca68a49f3a104fed5687ac35ab4e9ef759734beb26c65dd5bc9f4582367da9fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:54.584634Z","signature_b64":"nidL/65LNWbad+neG7h2kRWxdKulRAtvIgA0iEHn42+HE3WV9grHMENYhWNnUUr2iS2juAGDu2oWL0k+1zp5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90b8b9183b6b4a7db31eb69498931a91e05e4d7581aa09a08f909f1b5231cb0d","last_reissued_at":"2026-06-01T01:03:54.583539Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:54.583539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Adjacent-frame Eulerian motion fields with bidirectional cycle checks guide diffusion-based image animation without drift accumulation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyan Miao, Cong-Duy Nguyen, Khoi M. Le, Luu Anh Tuan, See-kiong Ng, Thong Nguyen","submitted_at":"2026-05-07T13:53:31Z","abstract_excerpt":"Recent advancements in image animation have utilized diffusion models to breathe life into static images. However, existing controllable frameworks typically rely on Lagrangian motion guidance, where optical flow is estimated relative to the initial frame. This paper revisits the same optical-flow primitive through a more local supervision design: we use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop. This shift enables parallelized training and provides bounded-error supervision throughout the generation process. To mit"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Using adjacent-frame Eulerian motion fields to guide generation enables parallelized training and provides bounded-error supervision throughout the generation process; the Bidirectional Geometric Consistency mechanism mathematically identifies and masks occluded regions, preventing the model from learning incorrect warping objectives.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The forward-backward cycle check reliably identifies occluded regions without missing subtle motions or introducing new artifacts that affect the final animation quality.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Eulerian adjacent-frame motion guidance plus bidirectional geometric consistency yields faster training and more coherent diffusion-based image animation than first-frame reference methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Adjacent-frame Eulerian motion fields with bidirectional cycle checks guide diffusion-based image animation without drift accumulation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f1f7e931f13dc634b9e3854bd628fb829cfe9086108a8bf45c431527249eba9c"},"source":{"id":"2605.06280","kind":"arxiv","version":4},"verdict":{"id":"762b23e9-a2e9-4fc4-8a7c-ba65c14d97cd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T06:51:17.146575Z","strongest_claim":"Using adjacent-frame Eulerian motion fields to guide generation enables parallelized training and provides bounded-error supervision throughout the generation process; the Bidirectional Geometric Consistency mechanism mathematically identifies and masks occluded regions, preventing the model from learning incorrect warping objectives.","one_line_summary":"Eulerian adjacent-frame motion guidance plus bidirectional geometric consistency yields faster training and more coherent diffusion-based image animation than first-frame reference methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The forward-backward cycle check reliably identifies occluded regions without missing subtle motions or introducing new artifacts that affect the final animation quality.","pith_extraction_headline":"Adjacent-frame Eulerian motion fields with bidirectional cycle checks guide diffusion-based image animation without drift accumulation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.06280/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T12:42:04.111396Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T08:34:14.343219Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:19.585134Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:49:44.384327Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"338cc35d9f0240a723d849d80e4ea448241edd34787e8a600d0e559172a998e3"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fd3d50f4c3add1b11d7a329b71d05d5bca2c35be16bee380877407502417c162"},"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":"2605.06280","created_at":"2026-06-01T01:03:54.583710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.06280v4","created_at":"2026-06-01T01:03:54.583710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06280","created_at":"2026-06-01T01:03:54.583710+00:00"},{"alias_kind":"pith_short_12","alias_value":"SC4LSGB3NNFH","created_at":"2026-06-01T01:03:54.583710+00:00"},{"alias_kind":"pith_short_16","alias_value":"SC4LSGB3NNFH3MY6","created_at":"2026-06-01T01:03:54.583710+00:00"},{"alias_kind":"pith_short_8","alias_value":"SC4LSGB3","created_at":"2026-06-01T01:03:54.583710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SC4LSGB3NNFH3MY6W2KJREY2SH","json":"https://pith.science/pith/SC4LSGB3NNFH3MY6W2KJREY2SH.json","graph_json":"https://pith.science/api/pith-number/SC4LSGB3NNFH3MY6W2KJREY2SH/graph.json","events_json":"https://pith.science/api/pith-number/SC4LSGB3NNFH3MY6W2KJREY2SH/events.json","paper":"https://pith.science/paper/SC4LSGB3"},"agent_actions":{"view_html":"https://pith.science/pith/SC4LSGB3NNFH3MY6W2KJREY2SH","download_json":"https://pith.science/pith/SC4LSGB3NNFH3MY6W2KJREY2SH.json","view_paper":"https://pith.science/paper/SC4LSGB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.06280&json=true","fetch_graph":"https://pith.science/api/pith-number/SC4LSGB3NNFH3MY6W2KJREY2SH/graph.json","fetch_events":"https://pith.science/api/pith-number/SC4LSGB3NNFH3MY6W2KJREY2SH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SC4LSGB3NNFH3MY6W2KJREY2SH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SC4LSGB3NNFH3MY6W2KJREY2SH/action/storage_attestation","attest_author":"https://pith.science/pith/SC4LSGB3NNFH3MY6W2KJREY2SH/action/author_attestation","sign_citation":"https://pith.science/pith/SC4LSGB3NNFH3MY6W2KJREY2SH/action/citation_signature","submit_replication":"https://pith.science/pith/SC4LSGB3NNFH3MY6W2KJREY2SH/action/replication_record"}},"created_at":"2026-06-01T01:03:54.583710+00:00","updated_at":"2026-06-01T01:03:54.583710+00:00"}