{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4RN5I4NBRJBR27SI3R4KSS2W2S","short_pith_number":"pith:4RN5I4NB","schema_version":"1.0","canonical_sha256":"e45bd471a18a431d7e48dc78a94b56d4a5e147683cb082743bade47c2fdd9de2","source":{"kind":"arxiv","id":"2605.14326","version":1},"attestation_state":"computed","paper":{"title":"D2-CDIG: Controlled Diffusion Remote Sensing Image Generation with Dual Priors of DEM and Cloud-Fog","license":"http://creativecommons.org/licenses/by/4.0/","headline":"D2-CDIG uses dual DEM and cloud-fog priors in diffusion models to control terrain and atmospheric features in remote sensing images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kanyaphakphachsorn Pharksuwan, Maocai Ning, Su Luo, Xiaoyu Li, Ying Liu, Zuopeng Zhao","submitted_at":"2026-05-14T03:41:46Z","abstract_excerpt":"Remote sensing image generation provides a reliable data foundation for remote sensing large models and downstream tasks. However, existing controllable remote sensing image generation methods typically rely on traditional techniques such as segmentation and edge detection, which do not fully leverage terrain or atmospheric conditions. As a result, the generated images often lack accuracy and naturalness when dealing with complex terrains and atmospheric phenomena. In this paper, we propose a novel remote sensing image generation framework, D2-CDIG, which integrates diffusion models with a dua"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T03:41:46Z","cross_cats_sorted":[],"title_canon_sha256":"e4a50f54cd410e2b2b4506f28a6e9cc3ec92a1a0d81ac549171a2a1bbde5746c","abstract_canon_sha256":"4fec2868b0235ae24e8467187ee8fce08a84bbd75ff20d1ceabfcad616479db5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:09.772952Z","signature_b64":"b5PA6OXgaaZJkWgS96r070uOGtPfSzkF94wPzQGbM2FincrykOo6qW5UyGz04EUTOTjRI4xpQ6I3QUKftxdaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e45bd471a18a431d7e48dc78a94b56d4a5e147683cb082743bade47c2fdd9de2","last_reissued_at":"2026-05-17T23:39:09.772289Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:09.772289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D2-CDIG: Controlled Diffusion Remote Sensing Image Generation with Dual Priors of DEM and Cloud-Fog","license":"http://creativecommons.org/licenses/by/4.0/","headline":"D2-CDIG uses dual DEM and cloud-fog priors in diffusion models to control terrain and atmospheric features in remote sensing images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kanyaphakphachsorn Pharksuwan, Maocai Ning, Su Luo, Xiaoyu Li, Ying Liu, Zuopeng Zhao","submitted_at":"2026-05-14T03:41:46Z","abstract_excerpt":"Remote sensing image generation provides a reliable data foundation for remote sensing large models and downstream tasks. However, existing controllable remote sensing image generation methods typically rely on traditional techniques such as segmentation and edge detection, which do not fully leverage terrain or atmospheric conditions. As a result, the generated images often lack accuracy and naturalness when dealing with complex terrains and atmospheric phenomena. In this paper, we propose a novel remote sensing image generation framework, D2-CDIG, which integrates diffusion models with a dua"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"D2-CDIG precisely controls ground features and atmospheric phenomena within the generated images by incorporating both DEM and cloud-fog information as dual prior knowledge, showing significant improvements in image quality, detail richness, and realism compared to traditional methods based on segmentation or edge detection.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That independent control of ground and atmospheric branches with layered injection of DEM and cloud-fog signals will produce seamless, artifact-free images without requiring post-hoc adjustments or introducing inconsistencies between terrain and atmosphere.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"D2-CDIG conditions diffusion models on DEM and cloud-fog priors to generate controlled remote sensing images with decoupled terrain and atmospheric control.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"D2-CDIG uses dual DEM and cloud-fog priors in diffusion models to control terrain and atmospheric features in remote sensing images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f7dadbce35001238fe4e74a217fc792cd0ee2b5149c22ea13ff0cb1a3739ea04"},"source":{"id":"2605.14326","kind":"arxiv","version":1},"verdict":{"id":"e2df401b-a2ae-424c-9e97-01a215a2fd5a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:11:36.716260Z","strongest_claim":"D2-CDIG precisely controls ground features and atmospheric phenomena within the generated images by incorporating both DEM and cloud-fog information as dual prior knowledge, showing significant improvements in image quality, detail richness, and realism compared to traditional methods based on segmentation or edge detection.","one_line_summary":"D2-CDIG conditions diffusion models on DEM and cloud-fog priors to generate controlled remote sensing images with decoupled terrain and atmospheric control.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That independent control of ground and atmospheric branches with layered injection of DEM and cloud-fog signals will produce seamless, artifact-free images without requiring post-hoc adjustments or introducing inconsistencies between terrain and atmosphere.","pith_extraction_headline":"D2-CDIG uses dual DEM and cloud-fog priors in diffusion models to control terrain and atmospheric features in remote sensing images."},"references":{"count":45,"sample":[{"doi":"","year":2023,"title":"Ambient diffusion: Learning clean distributions from corrupted data,","work_id":"e9428eaa-b758-484f-85f3-a9fa25511626","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"On creating benchmark dataset for aerial image interpre- tation: Reviews, guidances, and million-aid,","work_id":"241a234f-9d39-4c85-94c7-9cda4df778ce","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Crs-diff: Controllable remote sensing image generation with diffusion model,","work_id":"265770c7-3a85-40bf-927b-03523929e49d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Bird’s-eye view: Remote sensing insights into the impact of mowing events on eurasian curlew habitat selection,","work_id":"7192d46d-6298-4fa6-b6ff-c9d15de8ef8c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Spatiotemporal variation in land use land cover in the response to local climate change using multispectral remote sensing data,","work_id":"590c54d9-e777-4f10-a78a-6478291f12ac","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":45,"snapshot_sha256":"e2e1f76cc34d1fca485488eb3cb98a7a0e443acdf63b8a357ccad3e38b6fa5aa","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":"2605.14326","created_at":"2026-05-17T23:39:09.772407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14326v1","created_at":"2026-05-17T23:39:09.772407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14326","created_at":"2026-05-17T23:39:09.772407+00:00"},{"alias_kind":"pith_short_12","alias_value":"4RN5I4NBRJBR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"4RN5I4NBRJBR27SI","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"4RN5I4NB","created_at":"2026-05-18T12:33:37.589309+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/4RN5I4NBRJBR27SI3R4KSS2W2S","json":"https://pith.science/pith/4RN5I4NBRJBR27SI3R4KSS2W2S.json","graph_json":"https://pith.science/api/pith-number/4RN5I4NBRJBR27SI3R4KSS2W2S/graph.json","events_json":"https://pith.science/api/pith-number/4RN5I4NBRJBR27SI3R4KSS2W2S/events.json","paper":"https://pith.science/paper/4RN5I4NB"},"agent_actions":{"view_html":"https://pith.science/pith/4RN5I4NBRJBR27SI3R4KSS2W2S","download_json":"https://pith.science/pith/4RN5I4NBRJBR27SI3R4KSS2W2S.json","view_paper":"https://pith.science/paper/4RN5I4NB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14326&json=true","fetch_graph":"https://pith.science/api/pith-number/4RN5I4NBRJBR27SI3R4KSS2W2S/graph.json","fetch_events":"https://pith.science/api/pith-number/4RN5I4NBRJBR27SI3R4KSS2W2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4RN5I4NBRJBR27SI3R4KSS2W2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4RN5I4NBRJBR27SI3R4KSS2W2S/action/storage_attestation","attest_author":"https://pith.science/pith/4RN5I4NBRJBR27SI3R4KSS2W2S/action/author_attestation","sign_citation":"https://pith.science/pith/4RN5I4NBRJBR27SI3R4KSS2W2S/action/citation_signature","submit_replication":"https://pith.science/pith/4RN5I4NBRJBR27SI3R4KSS2W2S/action/replication_record"}},"created_at":"2026-05-17T23:39:09.772407+00:00","updated_at":"2026-05-17T23:39:09.772407+00:00"}