{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HAGA3BSRGFINW3G3FSEIKMWO42","short_pith_number":"pith:HAGA3BSR","schema_version":"1.0","canonical_sha256":"380c0d86513150db6cdb2c888532cee6af9ddf7b17eeb56691fbf3178c463201","source":{"kind":"arxiv","id":"1910.09139","version":1},"attestation_state":"computed","paper":{"title":"DwNet: Dense warp-based network for pose-guided human video generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Bo Zhao, Leonid Sigal, Polina Zablotskaia","submitted_at":"2019-10-21T03:56:51Z","abstract_excerpt":"Generation of realistic high-resolution videos of human subjects is a challenging and important task in computer vision. In this paper, we focus on human motion transfer - generation of a video depicting a particular subject, observed in a single image, performing a series of motions exemplified by an auxiliary (driving) video. Our GAN-based architecture, DwNet, leverages dense intermediate pose-guided representation and refinement process to warp the required subject appearance, in the form of the texture, from a source image into a desired pose. Temporal consistency is maintained by further "},"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":"1910.09139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-21T03:56:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1b3c3fa15213b30f3c7f5dfcdb44c29eec5098bfc088af713836908d8154ca06","abstract_canon_sha256":"8cc18319c0e5cf9c7961c59c2ceed7bed165df1d1a32d1b870870689dcb952cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:22.968286Z","signature_b64":"QCVg0CeLF09VROkHVoNDpu+kC0Ye4RE+ZAyFRCrox+x0CopAAQg324CeuooZvy4KgLpgFxvrKAIHvhqlOf4aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"380c0d86513150db6cdb2c888532cee6af9ddf7b17eeb56691fbf3178c463201","last_reissued_at":"2026-07-05T00:13:22.967807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:22.967807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DwNet: Dense warp-based network for pose-guided human video generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Bo Zhao, Leonid Sigal, Polina Zablotskaia","submitted_at":"2019-10-21T03:56:51Z","abstract_excerpt":"Generation of realistic high-resolution videos of human subjects is a challenging and important task in computer vision. In this paper, we focus on human motion transfer - generation of a video depicting a particular subject, observed in a single image, performing a series of motions exemplified by an auxiliary (driving) video. Our GAN-based architecture, DwNet, leverages dense intermediate pose-guided representation and refinement process to warp the required subject appearance, in the form of the texture, from a source image into a desired pose. Temporal consistency is maintained by further "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09139","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/1910.09139/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":"1910.09139","created_at":"2026-07-05T00:13:22.967864+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.09139v1","created_at":"2026-07-05T00:13:22.967864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09139","created_at":"2026-07-05T00:13:22.967864+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAGA3BSRGFIN","created_at":"2026-07-05T00:13:22.967864+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAGA3BSRGFINW3G3","created_at":"2026-07-05T00:13:22.967864+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAGA3BSR","created_at":"2026-07-05T00:13:22.967864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27192","citing_title":"LISA: Likelihood Score Alignment for Visual-condition Controllable Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15042","citing_title":"EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16042","citing_title":"Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22940","citing_title":"One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HAGA3BSRGFINW3G3FSEIKMWO42","json":"https://pith.science/pith/HAGA3BSRGFINW3G3FSEIKMWO42.json","graph_json":"https://pith.science/api/pith-number/HAGA3BSRGFINW3G3FSEIKMWO42/graph.json","events_json":"https://pith.science/api/pith-number/HAGA3BSRGFINW3G3FSEIKMWO42/events.json","paper":"https://pith.science/paper/HAGA3BSR"},"agent_actions":{"view_html":"https://pith.science/pith/HAGA3BSRGFINW3G3FSEIKMWO42","download_json":"https://pith.science/pith/HAGA3BSRGFINW3G3FSEIKMWO42.json","view_paper":"https://pith.science/paper/HAGA3BSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.09139&json=true","fetch_graph":"https://pith.science/api/pith-number/HAGA3BSRGFINW3G3FSEIKMWO42/graph.json","fetch_events":"https://pith.science/api/pith-number/HAGA3BSRGFINW3G3FSEIKMWO42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAGA3BSRGFINW3G3FSEIKMWO42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAGA3BSRGFINW3G3FSEIKMWO42/action/storage_attestation","attest_author":"https://pith.science/pith/HAGA3BSRGFINW3G3FSEIKMWO42/action/author_attestation","sign_citation":"https://pith.science/pith/HAGA3BSRGFINW3G3FSEIKMWO42/action/citation_signature","submit_replication":"https://pith.science/pith/HAGA3BSRGFINW3G3FSEIKMWO42/action/replication_record"}},"created_at":"2026-07-05T00:13:22.967864+00:00","updated_at":"2026-07-05T00:13:22.967864+00:00"}