{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:NPOWITF753YPTPHIJBWQXG6TW2","short_pith_number":"pith:NPOWITF7","schema_version":"1.0","canonical_sha256":"6bdd644cbfeef0f9bce8486d0b9bd3b682fd4467a386b2c88d1f274be6a19087","source":{"kind":"arxiv","id":"1611.01331","version":5},"attestation_state":"computed","paper":{"title":"RenderGAN: Generating Realistic Labeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Benjamin Wild, Leon Sixt, Tim Landgraf","submitted_at":"2016-11-04T11:20:38Z","abstract_excerpt":"Deep Convolutional Neuronal Networks (DCNNs) are showing remarkable performance on many computer vision tasks. Due to their large parameter space, they require many labeled samples when trained in a supervised setting. The costs of annotating data manually can render the use of DCNNs infeasible. We present a novel framework called RenderGAN that can generate large amounts of realistic, labeled images by combining a 3D model and the Generative Adversarial Network framework. In our approach, image augmentations (e.g. lighting, background, and detail) are learned from unlabeled data such that 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":"1611.01331","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-04T11:20:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e41de40797c52277113164a147e9a2735db33d004d03f1902c8064fee3d07f0a","abstract_canon_sha256":"016854d4095ee3bbeef89737535f4509a4af02db9acc63c376efd8df3080446b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:58.490262Z","signature_b64":"cIAonY/aVwiQGaUNsFzoo2pXqXGJeTZA2G9/QRX5ssBACFbutXCyzDkMlufseA9gYV5Rq95iSO3emYzq4O9wCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bdd644cbfeef0f9bce8486d0b9bd3b682fd4467a386b2c88d1f274be6a19087","last_reissued_at":"2026-05-18T00:52:58.489826Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:58.489826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RenderGAN: Generating Realistic Labeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Benjamin Wild, Leon Sixt, Tim Landgraf","submitted_at":"2016-11-04T11:20:38Z","abstract_excerpt":"Deep Convolutional Neuronal Networks (DCNNs) are showing remarkable performance on many computer vision tasks. Due to their large parameter space, they require many labeled samples when trained in a supervised setting. The costs of annotating data manually can render the use of DCNNs infeasible. We present a novel framework called RenderGAN that can generate large amounts of realistic, labeled images by combining a 3D model and the Generative Adversarial Network framework. In our approach, image augmentations (e.g. lighting, background, and detail) are learned from unlabeled data such that the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01331","kind":"arxiv","version":5},"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":"1611.01331","created_at":"2026-05-18T00:52:58.489886+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.01331v5","created_at":"2026-05-18T00:52:58.489886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01331","created_at":"2026-05-18T00:52:58.489886+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPOWITF753YP","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPOWITF753YPTPHI","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPOWITF7","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11172","citing_title":"Learning Data Augmentation Strategies for Object Detection","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPOWITF753YPTPHIJBWQXG6TW2","json":"https://pith.science/pith/NPOWITF753YPTPHIJBWQXG6TW2.json","graph_json":"https://pith.science/api/pith-number/NPOWITF753YPTPHIJBWQXG6TW2/graph.json","events_json":"https://pith.science/api/pith-number/NPOWITF753YPTPHIJBWQXG6TW2/events.json","paper":"https://pith.science/paper/NPOWITF7"},"agent_actions":{"view_html":"https://pith.science/pith/NPOWITF753YPTPHIJBWQXG6TW2","download_json":"https://pith.science/pith/NPOWITF753YPTPHIJBWQXG6TW2.json","view_paper":"https://pith.science/paper/NPOWITF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.01331&json=true","fetch_graph":"https://pith.science/api/pith-number/NPOWITF753YPTPHIJBWQXG6TW2/graph.json","fetch_events":"https://pith.science/api/pith-number/NPOWITF753YPTPHIJBWQXG6TW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPOWITF753YPTPHIJBWQXG6TW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPOWITF753YPTPHIJBWQXG6TW2/action/storage_attestation","attest_author":"https://pith.science/pith/NPOWITF753YPTPHIJBWQXG6TW2/action/author_attestation","sign_citation":"https://pith.science/pith/NPOWITF753YPTPHIJBWQXG6TW2/action/citation_signature","submit_replication":"https://pith.science/pith/NPOWITF753YPTPHIJBWQXG6TW2/action/replication_record"}},"created_at":"2026-05-18T00:52:58.489886+00:00","updated_at":"2026-05-18T00:52:58.489886+00:00"}