{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3ZJAHGJMHAQ3Z3BWPMEYCBOI2R","short_pith_number":"pith:3ZJAHGJM","schema_version":"1.0","canonical_sha256":"de5203992c3821bcec367b098105c8d4790f79120192f05c039de6af7d6e35d2","source":{"kind":"arxiv","id":"2208.13753","version":2},"attestation_state":"computed","paper":{"title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Lu Yuan, Wan-Cyuan Fan, Yen-Chun Chen, Yu Cheng, Yu-Chiang Frank Wang","submitted_at":"2022-08-29T17:37:29Z","abstract_excerpt":"Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a challenging task. In this paper, we present Frido, a Feature Pyramid Diffusion model performing a multi-scale coarse-to-fine denoising process for image synthesis. Our model decomposes an input image into scale-dependent vector quantized features, followed by a coarse-to-fine gating for producing image output. During the above multi-scale representation learning stag"},"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":"2208.13753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-29T17:37:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c7fa947d91c766b1a209b7153a861516148fb4371507f80f79ab7d4920699be6","abstract_canon_sha256":"614405ad0b070362ec9c4f6fd16b3e6474646ac1fe7cf4f6248760a065ae7325"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:27.140474Z","signature_b64":"55X9390Rn7ninSWgpOawKD5Fs7YOTqd8Z/1dh78M7hVMHUe9oxiU2c5yt+f1KqaIwiuZjT+C6CXfVPLE7ZFhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de5203992c3821bcec367b098105c8d4790f79120192f05c039de6af7d6e35d2","last_reissued_at":"2026-07-05T05:21:27.139967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:27.139967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Lu Yuan, Wan-Cyuan Fan, Yen-Chun Chen, Yu Cheng, Yu-Chiang Frank Wang","submitted_at":"2022-08-29T17:37:29Z","abstract_excerpt":"Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a challenging task. In this paper, we present Frido, a Feature Pyramid Diffusion model performing a multi-scale coarse-to-fine denoising process for image synthesis. Our model decomposes an input image into scale-dependent vector quantized features, followed by a coarse-to-fine gating for producing image output. During the above multi-scale representation learning stag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.13753","kind":"arxiv","version":2},"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/2208.13753/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":"2208.13753","created_at":"2026-07-05T05:21:27.140030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.13753v2","created_at":"2026-07-05T05:21:27.140030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.13753","created_at":"2026-07-05T05:21:27.140030+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZJAHGJMHAQ3","created_at":"2026-07-05T05:21:27.140030+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZJAHGJMHAQ3Z3BW","created_at":"2026-07-05T05:21:27.140030+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZJAHGJM","created_at":"2026-07-05T05:21:27.140030+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06962","citing_title":"AR-RAG: Autoregressive Retrieval Augmentation for Image Generation","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R","json":"https://pith.science/pith/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R.json","graph_json":"https://pith.science/api/pith-number/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R/graph.json","events_json":"https://pith.science/api/pith-number/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R/events.json","paper":"https://pith.science/paper/3ZJAHGJM"},"agent_actions":{"view_html":"https://pith.science/pith/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R","download_json":"https://pith.science/pith/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R.json","view_paper":"https://pith.science/paper/3ZJAHGJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.13753&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R/action/storage_attestation","attest_author":"https://pith.science/pith/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R/action/author_attestation","sign_citation":"https://pith.science/pith/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R/action/citation_signature","submit_replication":"https://pith.science/pith/3ZJAHGJMHAQ3Z3BWPMEYCBOI2R/action/replication_record"}},"created_at":"2026-07-05T05:21:27.140030+00:00","updated_at":"2026-07-05T05:21:27.140030+00:00"}