{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:A7VAFOL2GVH22V4NLWO52WKKDD","short_pith_number":"pith:A7VAFOL2","schema_version":"1.0","canonical_sha256":"07ea02b97a354fad578d5d9ddd594a18da19a1402e8b1e9344f295573581df38","source":{"kind":"arxiv","id":"1803.01837","version":1},"attestation_state":"computed","paper":{"title":"ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen-Hsuan Lin, Eli Shechtman, Ersin Yumer, Oliver Wang, Simon Lucey","submitted_at":"2018-03-05T18:59:01Z","abstract_excerpt":"We address the problem of finding realistic geometric corrections to a foreground object such that it appears natural when composited into a background image. To achieve this, we propose a novel Generative Adversarial Network (GAN) architecture that utilizes Spatial Transformer Networks (STNs) as the generator, which we call Spatial Transformer GANs (ST-GANs). ST-GANs seek image realism by operating in the geometric warp parameter space. In particular, we exploit an iterative STN warping scheme and propose a sequential training strategy that achieves better results compared to naive training o"},"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":"1803.01837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-05T18:59:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f62e8265dec4054767e20d1b9dcf7c23868ddec4c2cd441fb4657b31b31118a2","abstract_canon_sha256":"555d2dec8daa4650d0031dad1e25df59d1d3a3d7dea5fbfa222bde9846c11a13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:59.507267Z","signature_b64":"oaeW5I1CmlhjV664OyLUW9FNS/60+sWMZAtXf9VgOIiBJ0J+cC07WUuVCrdrNVxs6Goa45aejrAA54KyAApKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07ea02b97a354fad578d5d9ddd594a18da19a1402e8b1e9344f295573581df38","last_reissued_at":"2026-05-18T00:21:59.506601Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:59.506601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen-Hsuan Lin, Eli Shechtman, Ersin Yumer, Oliver Wang, Simon Lucey","submitted_at":"2018-03-05T18:59:01Z","abstract_excerpt":"We address the problem of finding realistic geometric corrections to a foreground object such that it appears natural when composited into a background image. To achieve this, we propose a novel Generative Adversarial Network (GAN) architecture that utilizes Spatial Transformer Networks (STNs) as the generator, which we call Spatial Transformer GANs (ST-GANs). ST-GANs seek image realism by operating in the geometric warp parameter space. In particular, we exploit an iterative STN warping scheme and propose a sequential training strategy that achieves better results compared to naive training o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01837","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":""},"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":"1803.01837","created_at":"2026-05-18T00:21:59.506708+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.01837v1","created_at":"2026-05-18T00:21:59.506708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01837","created_at":"2026-05-18T00:21:59.506708+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7VAFOL2GVH2","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7VAFOL2GVH22V4N","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7VAFOL2","created_at":"2026-05-18T12:32:13.499390+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/A7VAFOL2GVH22V4NLWO52WKKDD","json":"https://pith.science/pith/A7VAFOL2GVH22V4NLWO52WKKDD.json","graph_json":"https://pith.science/api/pith-number/A7VAFOL2GVH22V4NLWO52WKKDD/graph.json","events_json":"https://pith.science/api/pith-number/A7VAFOL2GVH22V4NLWO52WKKDD/events.json","paper":"https://pith.science/paper/A7VAFOL2"},"agent_actions":{"view_html":"https://pith.science/pith/A7VAFOL2GVH22V4NLWO52WKKDD","download_json":"https://pith.science/pith/A7VAFOL2GVH22V4NLWO52WKKDD.json","view_paper":"https://pith.science/paper/A7VAFOL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.01837&json=true","fetch_graph":"https://pith.science/api/pith-number/A7VAFOL2GVH22V4NLWO52WKKDD/graph.json","fetch_events":"https://pith.science/api/pith-number/A7VAFOL2GVH22V4NLWO52WKKDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7VAFOL2GVH22V4NLWO52WKKDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7VAFOL2GVH22V4NLWO52WKKDD/action/storage_attestation","attest_author":"https://pith.science/pith/A7VAFOL2GVH22V4NLWO52WKKDD/action/author_attestation","sign_citation":"https://pith.science/pith/A7VAFOL2GVH22V4NLWO52WKKDD/action/citation_signature","submit_replication":"https://pith.science/pith/A7VAFOL2GVH22V4NLWO52WKKDD/action/replication_record"}},"created_at":"2026-05-18T00:21:59.506708+00:00","updated_at":"2026-05-18T00:21:59.506708+00:00"}