{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:N62IT3IDIGFCYNUH2OQVXQWJNM","short_pith_number":"pith:N62IT3ID","schema_version":"1.0","canonical_sha256":"6fb489ed03418a2c3687d3a15bc2c96b0a943dc4fd7d2163afebd8086706df72","source":{"kind":"arxiv","id":"1808.06601","version":2},"attestation_state":"computed","paper":{"title":"Video-to-Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Bryan Catanzaro, Guilin Liu, Jan Kautz, Jun-Yan Zhu, Ming-Yu Liu, Ting-Chun Wang","submitted_at":"2018-08-20T17:58:42Z","abstract_excerpt":"We study the problem of video-to-video synthesis, whose goal is to learn a mapping function from an input source video (e.g., a sequence of semantic segmentation masks) to an output photorealistic video that precisely depicts the content of the source video. While its image counterpart, the image-to-image synthesis problem, is a popular topic, the video-to-video synthesis problem is less explored in the literature. Without understanding temporal dynamics, directly applying existing image synthesis approaches to an input video often results in temporally incoherent videos of low visual quality."},"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":"1808.06601","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-20T17:58:42Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"05b55246482c4b53dd997fd1f30976941354252a1ac8d40e187ea72064321116","abstract_canon_sha256":"5c44682d530122d8673bfe728657fb9c33fc564c0ac47547285637d58f8fd12d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:22.388490Z","signature_b64":"hC2GBto7G4JQEAhWih24LejAjk7m/AV5ZufDKisy0+fXxuTg6PlbfzSN0ozujKFwKYL0yF44Gv/g/GEKxlh9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fb489ed03418a2c3687d3a15bc2c96b0a943dc4fd7d2163afebd8086706df72","last_reissued_at":"2026-05-17T23:59:22.388111Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:22.388111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-to-Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Bryan Catanzaro, Guilin Liu, Jan Kautz, Jun-Yan Zhu, Ming-Yu Liu, Ting-Chun Wang","submitted_at":"2018-08-20T17:58:42Z","abstract_excerpt":"We study the problem of video-to-video synthesis, whose goal is to learn a mapping function from an input source video (e.g., a sequence of semantic segmentation masks) to an output photorealistic video that precisely depicts the content of the source video. While its image counterpart, the image-to-image synthesis problem, is a popular topic, the video-to-video synthesis problem is less explored in the literature. Without understanding temporal dynamics, directly applying existing image synthesis approaches to an input video often results in temporally incoherent videos of low visual quality."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.06601","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":""},"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":"1808.06601","created_at":"2026-05-17T23:59:22.388177+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.06601v2","created_at":"2026-05-17T23:59:22.388177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.06601","created_at":"2026-05-17T23:59:22.388177+00:00"},{"alias_kind":"pith_short_12","alias_value":"N62IT3IDIGFC","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"N62IT3IDIGFCYNUH","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"N62IT3ID","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04434","citing_title":"Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2104.10157","citing_title":"VideoGPT: Video Generation using VQ-VAE and Transformers","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07766","citing_title":"Head Similarity: Modeling Structured Whole-Head Appearance Beyond Face Recognition","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21291","citing_title":"Exploring the Role of Synthetic Data Augmentation in Controllable Human-Centric Video Generation","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N62IT3IDIGFCYNUH2OQVXQWJNM","json":"https://pith.science/pith/N62IT3IDIGFCYNUH2OQVXQWJNM.json","graph_json":"https://pith.science/api/pith-number/N62IT3IDIGFCYNUH2OQVXQWJNM/graph.json","events_json":"https://pith.science/api/pith-number/N62IT3IDIGFCYNUH2OQVXQWJNM/events.json","paper":"https://pith.science/paper/N62IT3ID"},"agent_actions":{"view_html":"https://pith.science/pith/N62IT3IDIGFCYNUH2OQVXQWJNM","download_json":"https://pith.science/pith/N62IT3IDIGFCYNUH2OQVXQWJNM.json","view_paper":"https://pith.science/paper/N62IT3ID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.06601&json=true","fetch_graph":"https://pith.science/api/pith-number/N62IT3IDIGFCYNUH2OQVXQWJNM/graph.json","fetch_events":"https://pith.science/api/pith-number/N62IT3IDIGFCYNUH2OQVXQWJNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N62IT3IDIGFCYNUH2OQVXQWJNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N62IT3IDIGFCYNUH2OQVXQWJNM/action/storage_attestation","attest_author":"https://pith.science/pith/N62IT3IDIGFCYNUH2OQVXQWJNM/action/author_attestation","sign_citation":"https://pith.science/pith/N62IT3IDIGFCYNUH2OQVXQWJNM/action/citation_signature","submit_replication":"https://pith.science/pith/N62IT3IDIGFCYNUH2OQVXQWJNM/action/replication_record"}},"created_at":"2026-05-17T23:59:22.388177+00:00","updated_at":"2026-05-17T23:59:22.388177+00:00"}