{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZUAXUOVHPVP4V2F36QBGO26FYM","short_pith_number":"pith:ZUAXUOVH","schema_version":"1.0","canonical_sha256":"cd017a3aa77d5fcae8bbf402676bc5c33609f0528f8aeebef4ebbdba30e37bbb","source":{"kind":"arxiv","id":"2106.09016","version":1},"attestation_state":"computed","paper":{"title":"Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bruno Lepri, Enver Sangineto, Haoxian Zhang, Linchao Bao, Marco De Nadai, Nicu Sebe, Wei Wang, Yahui Liu, Yajing Chen","submitted_at":"2021-06-16T17:58:21Z","abstract_excerpt":"Image-to-Image (I2I) multi-domain translation models are usually evaluated also using the quality of their semantic interpolation results. However, state-of-the-art models frequently show abrupt changes in the image appearance during interpolation, and usually perform poorly in interpolations across domains. In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The "},"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":"2106.09016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-16T17:58:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0210254e7c648b8cdae59b1f7654bfdfa095ad08ddd142c8c4203782c8f9d49","abstract_canon_sha256":"17c868b0b23550fa75bac70b303fdfd51fab6a5444df12c2ba09a9338aaf0eac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:03.667757Z","signature_b64":"rjed5GmFxDGiJtj5EBRk9boDK0aS0flCEhnA0go0JyFrMq4D13TKcnDUtpkIbDoczhjAuGEQLlj2tgTXCoPlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd017a3aa77d5fcae8bbf402676bc5c33609f0528f8aeebef4ebbdba30e37bbb","last_reissued_at":"2026-07-05T02:50:03.667303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:03.667303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bruno Lepri, Enver Sangineto, Haoxian Zhang, Linchao Bao, Marco De Nadai, Nicu Sebe, Wei Wang, Yahui Liu, Yajing Chen","submitted_at":"2021-06-16T17:58:21Z","abstract_excerpt":"Image-to-Image (I2I) multi-domain translation models are usually evaluated also using the quality of their semantic interpolation results. However, state-of-the-art models frequently show abrupt changes in the image appearance during interpolation, and usually perform poorly in interpolations across domains. In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09016","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/2106.09016/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":"2106.09016","created_at":"2026-07-05T02:50:03.667390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09016v1","created_at":"2026-07-05T02:50:03.667390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09016","created_at":"2026-07-05T02:50:03.667390+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUAXUOVHPVP4","created_at":"2026-07-05T02:50:03.667390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUAXUOVHPVP4V2F3","created_at":"2026-07-05T02:50:03.667390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUAXUOVH","created_at":"2026-07-05T02:50:03.667390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUAXUOVHPVP4V2F36QBGO26FYM","json":"https://pith.science/pith/ZUAXUOVHPVP4V2F36QBGO26FYM.json","graph_json":"https://pith.science/api/pith-number/ZUAXUOVHPVP4V2F36QBGO26FYM/graph.json","events_json":"https://pith.science/api/pith-number/ZUAXUOVHPVP4V2F36QBGO26FYM/events.json","paper":"https://pith.science/paper/ZUAXUOVH"},"agent_actions":{"view_html":"https://pith.science/pith/ZUAXUOVHPVP4V2F36QBGO26FYM","download_json":"https://pith.science/pith/ZUAXUOVHPVP4V2F36QBGO26FYM.json","view_paper":"https://pith.science/paper/ZUAXUOVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09016&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUAXUOVHPVP4V2F36QBGO26FYM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUAXUOVHPVP4V2F36QBGO26FYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUAXUOVHPVP4V2F36QBGO26FYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUAXUOVHPVP4V2F36QBGO26FYM/action/storage_attestation","attest_author":"https://pith.science/pith/ZUAXUOVHPVP4V2F36QBGO26FYM/action/author_attestation","sign_citation":"https://pith.science/pith/ZUAXUOVHPVP4V2F36QBGO26FYM/action/citation_signature","submit_replication":"https://pith.science/pith/ZUAXUOVHPVP4V2F36QBGO26FYM/action/replication_record"}},"created_at":"2026-07-05T02:50:03.667390+00:00","updated_at":"2026-07-05T02:50:03.667390+00:00"}