{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OMGHFXMYGXL6RKSFHLYR3ZA66D","short_pith_number":"pith:OMGHFXMY","schema_version":"1.0","canonical_sha256":"730c72dd9835d7e8aa453af11de41ef0da48c69da67b8cef691f09c264132b67","source":{"kind":"arxiv","id":"2405.14304","version":2},"attestation_state":"computed","paper":{"title":"Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.GR","authors_text":"Hans-Peter Seidel, Karol Myszkowski, Mojtaba Bemana, Thomas Leimk\\\"uhler, Tobias Ritschel","submitted_at":"2024-05-23T08:24:22Z","abstract_excerpt":"We demonstrate generating HDR images using the concerted action of multiple black-box, pre-trained LDR image diffusion models. Relying on a pre-trained LDR generative diffusion models is vital as, first, there is no sufficiently large HDR image dataset available to re-train them, and, second, even if it was, re-training such models is impossible for most compute budgets. Instead, we seek inspiration from the HDR image capture literature that traditionally fuses sets of LDR images, called \"exposure brackets'', to produce a single HDR image. We operate multiple denoising processes to generate mu"},"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":"2405.14304","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2024-05-23T08:24:22Z","cross_cats_sorted":["cs.CV","eess.IV"],"title_canon_sha256":"569604f037ead56d75393a6bf20ed320b05a95d2029534de20cde4509ae06085","abstract_canon_sha256":"0e41268e5e2227cbb2206b24fcb1f6d6077a9df14e9b2b29523eb364c3e02eca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:33.594354Z","signature_b64":"UwTHlruzGSSgdRDPumoqT1BjuCnL08zhP6RA6hn4AemE9mZ1ThDf6/AiBH5Bg6C8y32Qi9tIk6LZk/7vmMFUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"730c72dd9835d7e8aa453af11de41ef0da48c69da67b8cef691f09c264132b67","last_reissued_at":"2026-07-05T10:33:33.593854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:33.593854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.GR","authors_text":"Hans-Peter Seidel, Karol Myszkowski, Mojtaba Bemana, Thomas Leimk\\\"uhler, Tobias Ritschel","submitted_at":"2024-05-23T08:24:22Z","abstract_excerpt":"We demonstrate generating HDR images using the concerted action of multiple black-box, pre-trained LDR image diffusion models. Relying on a pre-trained LDR generative diffusion models is vital as, first, there is no sufficiently large HDR image dataset available to re-train them, and, second, even if it was, re-training such models is impossible for most compute budgets. Instead, we seek inspiration from the HDR image capture literature that traditionally fuses sets of LDR images, called \"exposure brackets'', to produce a single HDR image. We operate multiple denoising processes to generate mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14304","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/2405.14304/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":"2405.14304","created_at":"2026-07-05T10:33:33.593912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14304v2","created_at":"2026-07-05T10:33:33.593912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14304","created_at":"2026-07-05T10:33:33.593912+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMGHFXMYGXL6","created_at":"2026-07-05T10:33:33.593912+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMGHFXMYGXL6RKSF","created_at":"2026-07-05T10:33:33.593912+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMGHFXMY","created_at":"2026-07-05T10:33:33.593912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11115","citing_title":"LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06161","citing_title":"DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMGHFXMYGXL6RKSFHLYR3ZA66D","json":"https://pith.science/pith/OMGHFXMYGXL6RKSFHLYR3ZA66D.json","graph_json":"https://pith.science/api/pith-number/OMGHFXMYGXL6RKSFHLYR3ZA66D/graph.json","events_json":"https://pith.science/api/pith-number/OMGHFXMYGXL6RKSFHLYR3ZA66D/events.json","paper":"https://pith.science/paper/OMGHFXMY"},"agent_actions":{"view_html":"https://pith.science/pith/OMGHFXMYGXL6RKSFHLYR3ZA66D","download_json":"https://pith.science/pith/OMGHFXMYGXL6RKSFHLYR3ZA66D.json","view_paper":"https://pith.science/paper/OMGHFXMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14304&json=true","fetch_graph":"https://pith.science/api/pith-number/OMGHFXMYGXL6RKSFHLYR3ZA66D/graph.json","fetch_events":"https://pith.science/api/pith-number/OMGHFXMYGXL6RKSFHLYR3ZA66D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMGHFXMYGXL6RKSFHLYR3ZA66D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMGHFXMYGXL6RKSFHLYR3ZA66D/action/storage_attestation","attest_author":"https://pith.science/pith/OMGHFXMYGXL6RKSFHLYR3ZA66D/action/author_attestation","sign_citation":"https://pith.science/pith/OMGHFXMYGXL6RKSFHLYR3ZA66D/action/citation_signature","submit_replication":"https://pith.science/pith/OMGHFXMYGXL6RKSFHLYR3ZA66D/action/replication_record"}},"created_at":"2026-07-05T10:33:33.593912+00:00","updated_at":"2026-07-05T10:33:33.593912+00:00"}