{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XVH3D7OKMUDDSJW24LTYSMTLOI","short_pith_number":"pith:XVH3D7OK","schema_version":"1.0","canonical_sha256":"bd4fb1fdca65063926dae2e789326b7210aca8ee88b2b23cbc98f06eab3ff0bb","source":{"kind":"arxiv","id":"2507.20388","version":1},"attestation_state":"computed","paper":{"title":"ModalFormer: Multimodal Transformer for Low-Light Image Enhancement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandru Brateanu, Ciprian Orhei, Codruta Ancuti, Cosmin Ancuti, Raul Balmez","submitted_at":"2025-07-27T19:07:22Z","abstract_excerpt":"Low-light image enhancement (LLIE) is a fundamental yet challenging task due to the presence of noise, loss of detail, and poor contrast in images captured under insufficient lighting conditions. Recent methods often rely solely on pixel-level transformations of RGB images, neglecting the rich contextual information available from multiple visual modalities. In this paper, we present ModalFormer, the first large-scale multimodal framework for LLIE that fully exploits nine auxiliary modalities to achieve state-of-the-art performance. Our model comprises two main components: a Cross-modal Transf"},"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":"2507.20388","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T19:07:22Z","cross_cats_sorted":[],"title_canon_sha256":"81f16f5e394f27915695f9670e424a49e10ccf00ed3cc62eb3e962c6ce9b666a","abstract_canon_sha256":"c77f8c294060303473afd0188130bac32cd50a124082d73c2ecdb291a42b4004"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:18.406816Z","signature_b64":"J0HYxZofrX49l6M2ikNtsPS98tjoiwy/PDuVzjA1VgtPm0nIhfMHa+o6xbNTasUw5ez1Bv/NwY1OLQPWKnvsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd4fb1fdca65063926dae2e789326b7210aca8ee88b2b23cbc98f06eab3ff0bb","last_reissued_at":"2026-07-05T11:44:18.406442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:18.406442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ModalFormer: Multimodal Transformer for Low-Light Image Enhancement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandru Brateanu, Ciprian Orhei, Codruta Ancuti, Cosmin Ancuti, Raul Balmez","submitted_at":"2025-07-27T19:07:22Z","abstract_excerpt":"Low-light image enhancement (LLIE) is a fundamental yet challenging task due to the presence of noise, loss of detail, and poor contrast in images captured under insufficient lighting conditions. Recent methods often rely solely on pixel-level transformations of RGB images, neglecting the rich contextual information available from multiple visual modalities. In this paper, we present ModalFormer, the first large-scale multimodal framework for LLIE that fully exploits nine auxiliary modalities to achieve state-of-the-art performance. Our model comprises two main components: a Cross-modal Transf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20388","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/2507.20388/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":"2507.20388","created_at":"2026-07-05T11:44:18.406500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20388v1","created_at":"2026-07-05T11:44:18.406500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20388","created_at":"2026-07-05T11:44:18.406500+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVH3D7OKMUDD","created_at":"2026-07-05T11:44:18.406500+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVH3D7OKMUDDSJW2","created_at":"2026-07-05T11:44:18.406500+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVH3D7OK","created_at":"2026-07-05T11:44:18.406500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17669","citing_title":"Low Light Image Enhancement Challenge at NTIRE 2026","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12556","citing_title":"M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17669","citing_title":"Low Light Image Enhancement Challenge at NTIRE 2026","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVH3D7OKMUDDSJW24LTYSMTLOI","json":"https://pith.science/pith/XVH3D7OKMUDDSJW24LTYSMTLOI.json","graph_json":"https://pith.science/api/pith-number/XVH3D7OKMUDDSJW24LTYSMTLOI/graph.json","events_json":"https://pith.science/api/pith-number/XVH3D7OKMUDDSJW24LTYSMTLOI/events.json","paper":"https://pith.science/paper/XVH3D7OK"},"agent_actions":{"view_html":"https://pith.science/pith/XVH3D7OKMUDDSJW24LTYSMTLOI","download_json":"https://pith.science/pith/XVH3D7OKMUDDSJW24LTYSMTLOI.json","view_paper":"https://pith.science/paper/XVH3D7OK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20388&json=true","fetch_graph":"https://pith.science/api/pith-number/XVH3D7OKMUDDSJW24LTYSMTLOI/graph.json","fetch_events":"https://pith.science/api/pith-number/XVH3D7OKMUDDSJW24LTYSMTLOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVH3D7OKMUDDSJW24LTYSMTLOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVH3D7OKMUDDSJW24LTYSMTLOI/action/storage_attestation","attest_author":"https://pith.science/pith/XVH3D7OKMUDDSJW24LTYSMTLOI/action/author_attestation","sign_citation":"https://pith.science/pith/XVH3D7OKMUDDSJW24LTYSMTLOI/action/citation_signature","submit_replication":"https://pith.science/pith/XVH3D7OKMUDDSJW24LTYSMTLOI/action/replication_record"}},"created_at":"2026-07-05T11:44:18.406500+00:00","updated_at":"2026-07-05T11:44:18.406500+00:00"}