{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XXZDBBQDBBB4ECJBSHDNC3XCB6","short_pith_number":"pith:XXZDBBQD","schema_version":"1.0","canonical_sha256":"bdf23086030843c2092191c6d16ee20f8b614287fe32dec766f8afead2b60a0c","source":{"kind":"arxiv","id":"2303.17559","version":2},"attestation_state":"computed","paper":{"title":"DDP: Diffusion Model for Dense Visual Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enze Xie, Lanqing Hong, Ping Luo, Tong Lu, Xihui Liu, Yuanfeng Ji, Zhaoqiang Liu, Zhe Chen, Zhenguo Li","submitted_at":"2023-03-30T17:26:50Z","abstract_excerpt":"We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. Our approach follows a \"noise-to-map\" generative paradigm for prediction by progressively removing noise from a random Gaussian distribution, guided by the image. The method, called DDP, efficiently extends the denoising diffusion process into the modern perception pipeline. Without task-specific design and architecture customization, DDP is easy to generalize to most dense prediction tasks, e.g., semantic segmentation and depth estimation. In addition, DDP shows att"},"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":"2303.17559","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T17:26:50Z","cross_cats_sorted":[],"title_canon_sha256":"912f4033a715ab7901a62613eaa9c07375f489b9a096db20d9c6fcb6249758ab","abstract_canon_sha256":"26c83159a41c736e11b7f1c111a4696e34f5c0dcc9b4645061de3e625ec98821"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:50.013043Z","signature_b64":"+XxogWGgBj8plRE7uU5Jo7crxyTYcizpWIVOPen9kNtmJIcHcmOO6NcMy3n1rwJ2NJ4cGt0slFruxgWzcf8zAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdf23086030843c2092191c6d16ee20f8b614287fe32dec766f8afead2b60a0c","last_reissued_at":"2026-07-05T06:09:50.012638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:50.012638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DDP: Diffusion Model for Dense Visual Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enze Xie, Lanqing Hong, Ping Luo, Tong Lu, Xihui Liu, Yuanfeng Ji, Zhaoqiang Liu, Zhe Chen, Zhenguo Li","submitted_at":"2023-03-30T17:26:50Z","abstract_excerpt":"We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. Our approach follows a \"noise-to-map\" generative paradigm for prediction by progressively removing noise from a random Gaussian distribution, guided by the image. The method, called DDP, efficiently extends the denoising diffusion process into the modern perception pipeline. Without task-specific design and architecture customization, DDP is easy to generalize to most dense prediction tasks, e.g., semantic segmentation and depth estimation. In addition, DDP shows att"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17559","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/2303.17559/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":"2303.17559","created_at":"2026-07-05T06:09:50.012693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17559v2","created_at":"2026-07-05T06:09:50.012693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17559","created_at":"2026-07-05T06:09:50.012693+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXZDBBQDBBB4","created_at":"2026-07-05T06:09:50.012693+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXZDBBQDBBB4ECJB","created_at":"2026-07-05T06:09:50.012693+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXZDBBQD","created_at":"2026-07-05T06:09:50.012693+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/XXZDBBQDBBB4ECJBSHDNC3XCB6","json":"https://pith.science/pith/XXZDBBQDBBB4ECJBSHDNC3XCB6.json","graph_json":"https://pith.science/api/pith-number/XXZDBBQDBBB4ECJBSHDNC3XCB6/graph.json","events_json":"https://pith.science/api/pith-number/XXZDBBQDBBB4ECJBSHDNC3XCB6/events.json","paper":"https://pith.science/paper/XXZDBBQD"},"agent_actions":{"view_html":"https://pith.science/pith/XXZDBBQDBBB4ECJBSHDNC3XCB6","download_json":"https://pith.science/pith/XXZDBBQDBBB4ECJBSHDNC3XCB6.json","view_paper":"https://pith.science/paper/XXZDBBQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17559&json=true","fetch_graph":"https://pith.science/api/pith-number/XXZDBBQDBBB4ECJBSHDNC3XCB6/graph.json","fetch_events":"https://pith.science/api/pith-number/XXZDBBQDBBB4ECJBSHDNC3XCB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXZDBBQDBBB4ECJBSHDNC3XCB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXZDBBQDBBB4ECJBSHDNC3XCB6/action/storage_attestation","attest_author":"https://pith.science/pith/XXZDBBQDBBB4ECJBSHDNC3XCB6/action/author_attestation","sign_citation":"https://pith.science/pith/XXZDBBQDBBB4ECJBSHDNC3XCB6/action/citation_signature","submit_replication":"https://pith.science/pith/XXZDBBQDBBB4ECJBSHDNC3XCB6/action/replication_record"}},"created_at":"2026-07-05T06:09:50.012693+00:00","updated_at":"2026-07-05T06:09:50.012693+00:00"}