{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IUIYKMD5FLJ2RYNBJLDTDUT5GG","short_pith_number":"pith:IUIYKMD5","schema_version":"1.0","canonical_sha256":"451185307d2ad3a8e1a14ac731d27d31bb7fa6efebca972895dd5652e0348d46","source":{"kind":"arxiv","id":"2407.16308","version":1},"attestation_state":"computed","paper":{"title":"SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Bo Li, Hao Zhang, Hong Gu, Jinwei Chen, Lingtong Kong, Yike Xiong","submitted_at":"2024-07-23T09:02:35Z","abstract_excerpt":"Multi-exposure High Dynamic Range (HDR) imaging is a challenging task when facing truncated texture and complex motion. Existing deep learning-based methods have achieved great success by either following the alignment and fusion pipeline or utilizing attention mechanism. However, the large computation cost and inference delay hinder them from deploying on resource limited devices. In this paper, to achieve better efficiency, a novel Selective Alignment Fusion Network (SAFNet) for HDR imaging is proposed. After extracting pyramid features, it jointly refines valuable area masks and cross-expos"},"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":"2407.16308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T09:02:35Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"b09c892cd5906cb4d43adbc2191eead271a041ef0ed042d8881bb3a60d5ed76c","abstract_canon_sha256":"5cb36a086d20ff0451d88cc59fbff88788b61d740335281d697dc9b0ad1bc39a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:31.251374Z","signature_b64":"9NaX/iGokCYQfGW34DQkg05zNF5lqjwpFh1Rrpuxanlh9yF5nvCBW4xsFzVZgxSbycRfxtiOG6CI9Tk5qrlOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"451185307d2ad3a8e1a14ac731d27d31bb7fa6efebca972895dd5652e0348d46","last_reissued_at":"2026-07-05T08:47:31.250888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:31.250888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Bo Li, Hao Zhang, Hong Gu, Jinwei Chen, Lingtong Kong, Yike Xiong","submitted_at":"2024-07-23T09:02:35Z","abstract_excerpt":"Multi-exposure High Dynamic Range (HDR) imaging is a challenging task when facing truncated texture and complex motion. Existing deep learning-based methods have achieved great success by either following the alignment and fusion pipeline or utilizing attention mechanism. However, the large computation cost and inference delay hinder them from deploying on resource limited devices. In this paper, to achieve better efficiency, a novel Selective Alignment Fusion Network (SAFNet) for HDR imaging is proposed. After extracting pyramid features, it jointly refines valuable area masks and cross-expos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16308","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/2407.16308/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":"2407.16308","created_at":"2026-07-05T08:47:31.250946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16308v1","created_at":"2026-07-05T08:47:31.250946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16308","created_at":"2026-07-05T08:47:31.250946+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUIYKMD5FLJ2","created_at":"2026-07-05T08:47:31.250946+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUIYKMD5FLJ2RYNB","created_at":"2026-07-05T08:47:31.250946+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUIYKMD5","created_at":"2026-07-05T08:47:31.250946+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06161","citing_title":"DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUIYKMD5FLJ2RYNBJLDTDUT5GG","json":"https://pith.science/pith/IUIYKMD5FLJ2RYNBJLDTDUT5GG.json","graph_json":"https://pith.science/api/pith-number/IUIYKMD5FLJ2RYNBJLDTDUT5GG/graph.json","events_json":"https://pith.science/api/pith-number/IUIYKMD5FLJ2RYNBJLDTDUT5GG/events.json","paper":"https://pith.science/paper/IUIYKMD5"},"agent_actions":{"view_html":"https://pith.science/pith/IUIYKMD5FLJ2RYNBJLDTDUT5GG","download_json":"https://pith.science/pith/IUIYKMD5FLJ2RYNBJLDTDUT5GG.json","view_paper":"https://pith.science/paper/IUIYKMD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16308&json=true","fetch_graph":"https://pith.science/api/pith-number/IUIYKMD5FLJ2RYNBJLDTDUT5GG/graph.json","fetch_events":"https://pith.science/api/pith-number/IUIYKMD5FLJ2RYNBJLDTDUT5GG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUIYKMD5FLJ2RYNBJLDTDUT5GG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUIYKMD5FLJ2RYNBJLDTDUT5GG/action/storage_attestation","attest_author":"https://pith.science/pith/IUIYKMD5FLJ2RYNBJLDTDUT5GG/action/author_attestation","sign_citation":"https://pith.science/pith/IUIYKMD5FLJ2RYNBJLDTDUT5GG/action/citation_signature","submit_replication":"https://pith.science/pith/IUIYKMD5FLJ2RYNBJLDTDUT5GG/action/replication_record"}},"created_at":"2026-07-05T08:47:31.250946+00:00","updated_at":"2026-07-05T08:47:31.250946+00:00"}