{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YYAYW2PFBUDUJV2GJLIPPQL3KI","short_pith_number":"pith:YYAYW2PF","schema_version":"1.0","canonical_sha256":"c6018b69e50d0744d7464ad0f7c17b52286b23f7bf702050c5a5d32c64d7b747","source":{"kind":"arxiv","id":"2411.15580","version":3},"attestation_state":"computed","paper":{"title":"TKG-DM: Training-free Chroma Key Content Generation Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Dengel, Brian Bernhard Moser, Jinjia Zhou, Ko Watanabe, Ryugo Morita, Stanislav Frolov, Takahiro Shirakawa","submitted_at":"2024-11-23T15:07:15Z","abstract_excerpt":"Diffusion models have enabled the generation of high-quality images with a strong focus on realism and textual fidelity. Yet, large-scale text-to-image models, such as Stable Diffusion, struggle to generate images where foreground objects are placed over a chroma key background, limiting their ability to separate foreground and background elements without fine-tuning. To address this limitation, we present a novel Training-Free Chroma Key Content Generation Diffusion Model (TKG-DM), which optimizes the initial random noise to produce images with foreground objects on a specifiable color backgr"},"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":"2411.15580","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-23T15:07:15Z","cross_cats_sorted":[],"title_canon_sha256":"d5e74b84bfdbd7bac0b653be9162aee754246a94c8be60534c8c52c128eb7405","abstract_canon_sha256":"f947d6e37e3257c17aed7ee5910ebed945e30da19b0234f721593506bfde8518"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:15.884341Z","signature_b64":"aKB+wK1siaIf5RSaot7HNxTZRcA2NqtJqF3ZRq+DZY5kXjN9snE180X3xFoJswGdhyldHMcvttfWSsp/HZ6nCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6018b69e50d0744d7464ad0f7c17b52286b23f7bf702050c5a5d32c64d7b747","last_reissued_at":"2026-07-05T11:47:15.883829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:15.883829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TKG-DM: Training-free Chroma Key Content Generation Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Dengel, Brian Bernhard Moser, Jinjia Zhou, Ko Watanabe, Ryugo Morita, Stanislav Frolov, Takahiro Shirakawa","submitted_at":"2024-11-23T15:07:15Z","abstract_excerpt":"Diffusion models have enabled the generation of high-quality images with a strong focus on realism and textual fidelity. Yet, large-scale text-to-image models, such as Stable Diffusion, struggle to generate images where foreground objects are placed over a chroma key background, limiting their ability to separate foreground and background elements without fine-tuning. To address this limitation, we present a novel Training-Free Chroma Key Content Generation Diffusion Model (TKG-DM), which optimizes the initial random noise to produce images with foreground objects on a specifiable color backgr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15580","kind":"arxiv","version":3},"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/2411.15580/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":"2411.15580","created_at":"2026-07-05T11:47:15.883892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15580v3","created_at":"2026-07-05T11:47:15.883892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15580","created_at":"2026-07-05T11:47:15.883892+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYAYW2PFBUDU","created_at":"2026-07-05T11:47:15.883892+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYAYW2PFBUDUJV2G","created_at":"2026-07-05T11:47:15.883892+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYAYW2PF","created_at":"2026-07-05T11:47:15.883892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19392","citing_title":"HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYAYW2PFBUDUJV2GJLIPPQL3KI","json":"https://pith.science/pith/YYAYW2PFBUDUJV2GJLIPPQL3KI.json","graph_json":"https://pith.science/api/pith-number/YYAYW2PFBUDUJV2GJLIPPQL3KI/graph.json","events_json":"https://pith.science/api/pith-number/YYAYW2PFBUDUJV2GJLIPPQL3KI/events.json","paper":"https://pith.science/paper/YYAYW2PF"},"agent_actions":{"view_html":"https://pith.science/pith/YYAYW2PFBUDUJV2GJLIPPQL3KI","download_json":"https://pith.science/pith/YYAYW2PFBUDUJV2GJLIPPQL3KI.json","view_paper":"https://pith.science/paper/YYAYW2PF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15580&json=true","fetch_graph":"https://pith.science/api/pith-number/YYAYW2PFBUDUJV2GJLIPPQL3KI/graph.json","fetch_events":"https://pith.science/api/pith-number/YYAYW2PFBUDUJV2GJLIPPQL3KI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYAYW2PFBUDUJV2GJLIPPQL3KI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYAYW2PFBUDUJV2GJLIPPQL3KI/action/storage_attestation","attest_author":"https://pith.science/pith/YYAYW2PFBUDUJV2GJLIPPQL3KI/action/author_attestation","sign_citation":"https://pith.science/pith/YYAYW2PFBUDUJV2GJLIPPQL3KI/action/citation_signature","submit_replication":"https://pith.science/pith/YYAYW2PFBUDUJV2GJLIPPQL3KI/action/replication_record"}},"created_at":"2026-07-05T11:47:15.883892+00:00","updated_at":"2026-07-05T11:47:15.883892+00:00"}