{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IE2KBEC6WXICZEHTVU7KVEL737","short_pith_number":"pith:IE2KBEC6","schema_version":"1.0","canonical_sha256":"4134a0905eb5d02c90f3ad3eaa917fdff16aac618f7ceb5396eadbda4bcfffdf","source":{"kind":"arxiv","id":"2403.03485","version":1},"attestation_state":"computed","paper":{"title":"NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Seiichi Uchida, Takahiro Shirakawa","submitted_at":"2024-03-06T05:56:31Z","abstract_excerpt":"Layout-aware text-to-image generation is a task to generate multi-object images that reflect layout conditions in addition to text conditions. The current layout-aware text-to-image diffusion models still have several issues, including mismatches between the text and layout conditions and quality degradation of generated images. This paper proposes a novel layout-aware text-to-image diffusion model called NoiseCollage to tackle these issues. During the denoising process, NoiseCollage independently estimates noises for individual objects and then crops and merges them into a single noise. This "},"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":"2403.03485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-06T05:56:31Z","cross_cats_sorted":[],"title_canon_sha256":"fbe29c031be2815ed607329328008c21a14a3d3994da09298c582a1cf3967e63","abstract_canon_sha256":"53c9ef606acebc696ab16ac7f87b4dd04f018225c34a7eb27797ed5e6a65e067"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:48.877700Z","signature_b64":"ryaUZanhTdRR/QjSMoqtXYxAUs5ogdP2RnUKdrfBNXIg9Qs15GAqC+K9DyiDHWkk3g3eddly+XDHg4GspUsZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4134a0905eb5d02c90f3ad3eaa917fdff16aac618f7ceb5396eadbda4bcfffdf","last_reissued_at":"2026-07-05T07:52:48.877270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:48.877270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Seiichi Uchida, Takahiro Shirakawa","submitted_at":"2024-03-06T05:56:31Z","abstract_excerpt":"Layout-aware text-to-image generation is a task to generate multi-object images that reflect layout conditions in addition to text conditions. The current layout-aware text-to-image diffusion models still have several issues, including mismatches between the text and layout conditions and quality degradation of generated images. This paper proposes a novel layout-aware text-to-image diffusion model called NoiseCollage to tackle these issues. During the denoising process, NoiseCollage independently estimates noises for individual objects and then crops and merges them into a single noise. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03485","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/2403.03485/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":"2403.03485","created_at":"2026-07-05T07:52:48.877326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03485v1","created_at":"2026-07-05T07:52:48.877326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03485","created_at":"2026-07-05T07:52:48.877326+00:00"},{"alias_kind":"pith_short_12","alias_value":"IE2KBEC6WXIC","created_at":"2026-07-05T07:52:48.877326+00:00"},{"alias_kind":"pith_short_16","alias_value":"IE2KBEC6WXICZEHT","created_at":"2026-07-05T07:52:48.877326+00:00"},{"alias_kind":"pith_short_8","alias_value":"IE2KBEC6","created_at":"2026-07-05T07:52:48.877326+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/IE2KBEC6WXICZEHTVU7KVEL737","json":"https://pith.science/pith/IE2KBEC6WXICZEHTVU7KVEL737.json","graph_json":"https://pith.science/api/pith-number/IE2KBEC6WXICZEHTVU7KVEL737/graph.json","events_json":"https://pith.science/api/pith-number/IE2KBEC6WXICZEHTVU7KVEL737/events.json","paper":"https://pith.science/paper/IE2KBEC6"},"agent_actions":{"view_html":"https://pith.science/pith/IE2KBEC6WXICZEHTVU7KVEL737","download_json":"https://pith.science/pith/IE2KBEC6WXICZEHTVU7KVEL737.json","view_paper":"https://pith.science/paper/IE2KBEC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03485&json=true","fetch_graph":"https://pith.science/api/pith-number/IE2KBEC6WXICZEHTVU7KVEL737/graph.json","fetch_events":"https://pith.science/api/pith-number/IE2KBEC6WXICZEHTVU7KVEL737/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IE2KBEC6WXICZEHTVU7KVEL737/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IE2KBEC6WXICZEHTVU7KVEL737/action/storage_attestation","attest_author":"https://pith.science/pith/IE2KBEC6WXICZEHTVU7KVEL737/action/author_attestation","sign_citation":"https://pith.science/pith/IE2KBEC6WXICZEHTVU7KVEL737/action/citation_signature","submit_replication":"https://pith.science/pith/IE2KBEC6WXICZEHTVU7KVEL737/action/replication_record"}},"created_at":"2026-07-05T07:52:48.877326+00:00","updated_at":"2026-07-05T07:52:48.877326+00:00"}