{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D2QRXCHJFA2F6NZMRD5KTG7HMS","short_pith_number":"pith:D2QRXCHJ","schema_version":"1.0","canonical_sha256":"1ea11b88e928345f372c88faa99be764b70065ecdcebbc043c21f376849ee8fe","source":{"kind":"arxiv","id":"2403.09194","version":2},"attestation_state":"computed","paper":{"title":"Intention-driven Ego-to-Exo Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongchen Luo, Kai Zhu, Wei Zhai, Yang Cao","submitted_at":"2024-03-14T09:07:31Z","abstract_excerpt":"Ego-to-exo video generation refers to generating the corresponding exocentric video according to the egocentric video, providing valuable applications in AR/VR and embodied AI. Benefiting from advancements in diffusion model techniques, notable progress has been achieved in video generation. However, existing methods build upon the spatiotemporal consistency assumptions between adjacent frames, which cannot be satisfied in the ego-to-exo scenarios due to drastic changes in views. To this end, this paper proposes an Intention-Driven Ego-to-exo video generation framework (IDE) that leverages act"},"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":"2403.09194","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T09:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"a05782cf16468d706055a431c0886a33866373b20c592bf34b9b2b958232fde4","abstract_canon_sha256":"5eaa47d70e3b9035a4d2415e68bc2afba380db7d313cc6ca559a690fe11099ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:02.245533Z","signature_b64":"/lXJBvOsNBhv3y8rS9pTTuG9AEQmCTXmWXb7eV05Uf1OyNp7/uoHTe1/D9kblR6td3XQHibv3Oh4DVhV6ljqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ea11b88e928345f372c88faa99be764b70065ecdcebbc043c21f376849ee8fe","last_reissued_at":"2026-07-05T07:57:02.244962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:02.244962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intention-driven Ego-to-Exo Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongchen Luo, Kai Zhu, Wei Zhai, Yang Cao","submitted_at":"2024-03-14T09:07:31Z","abstract_excerpt":"Ego-to-exo video generation refers to generating the corresponding exocentric video according to the egocentric video, providing valuable applications in AR/VR and embodied AI. Benefiting from advancements in diffusion model techniques, notable progress has been achieved in video generation. However, existing methods build upon the spatiotemporal consistency assumptions between adjacent frames, which cannot be satisfied in the ego-to-exo scenarios due to drastic changes in views. To this end, this paper proposes an Intention-Driven Ego-to-exo video generation framework (IDE) that leverages act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09194","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/2403.09194/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":"2403.09194","created_at":"2026-07-05T07:57:02.245119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09194v2","created_at":"2026-07-05T07:57:02.245119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09194","created_at":"2026-07-05T07:57:02.245119+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2QRXCHJFA2F","created_at":"2026-07-05T07:57:02.245119+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2QRXCHJFA2F6NZM","created_at":"2026-07-05T07:57:02.245119+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2QRXCHJ","created_at":"2026-07-05T07:57:02.245119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26316","citing_title":"E$^3$C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13793","citing_title":"From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2QRXCHJFA2F6NZMRD5KTG7HMS","json":"https://pith.science/pith/D2QRXCHJFA2F6NZMRD5KTG7HMS.json","graph_json":"https://pith.science/api/pith-number/D2QRXCHJFA2F6NZMRD5KTG7HMS/graph.json","events_json":"https://pith.science/api/pith-number/D2QRXCHJFA2F6NZMRD5KTG7HMS/events.json","paper":"https://pith.science/paper/D2QRXCHJ"},"agent_actions":{"view_html":"https://pith.science/pith/D2QRXCHJFA2F6NZMRD5KTG7HMS","download_json":"https://pith.science/pith/D2QRXCHJFA2F6NZMRD5KTG7HMS.json","view_paper":"https://pith.science/paper/D2QRXCHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09194&json=true","fetch_graph":"https://pith.science/api/pith-number/D2QRXCHJFA2F6NZMRD5KTG7HMS/graph.json","fetch_events":"https://pith.science/api/pith-number/D2QRXCHJFA2F6NZMRD5KTG7HMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2QRXCHJFA2F6NZMRD5KTG7HMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2QRXCHJFA2F6NZMRD5KTG7HMS/action/storage_attestation","attest_author":"https://pith.science/pith/D2QRXCHJFA2F6NZMRD5KTG7HMS/action/author_attestation","sign_citation":"https://pith.science/pith/D2QRXCHJFA2F6NZMRD5KTG7HMS/action/citation_signature","submit_replication":"https://pith.science/pith/D2QRXCHJFA2F6NZMRD5KTG7HMS/action/replication_record"}},"created_at":"2026-07-05T07:57:02.245119+00:00","updated_at":"2026-07-05T07:57:02.245119+00:00"}