{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6XCWGOOPCTEQHZBNYICWWOZP6E","short_pith_number":"pith:6XCWGOOP","canonical_record":{"source":{"id":"2605.13049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T06:12:46Z","cross_cats_sorted":[],"title_canon_sha256":"2a1c743aad3f0f166a19d2d3344a68c0ede573e1c3f56fe40fa96f9ca2e339b9","abstract_canon_sha256":"034d636cd433ece28165d556b00860a79338f5eeba309e27ff61a6c16926b8a8"},"schema_version":"1.0"},"canonical_sha256":"f5c56339cf14c903e42dc2056b3b2ff124c41990778d5b3b8e1c7c012eef99da","source":{"kind":"arxiv","id":"2605.13049","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13049","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13049v1","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13049","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"6XCWGOOPCTEQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6XCWGOOPCTEQHZBN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6XCWGOOP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6XCWGOOPCTEQHZBNYICWWOZP6E","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T06:12:46Z","cross_cats_sorted":[],"title_canon_sha256":"2a1c743aad3f0f166a19d2d3344a68c0ede573e1c3f56fe40fa96f9ca2e339b9","abstract_canon_sha256":"034d636cd433ece28165d556b00860a79338f5eeba309e27ff61a6c16926b8a8"},"schema_version":"1.0"},"canonical_sha256":"f5c56339cf14c903e42dc2056b3b2ff124c41990778d5b3b8e1c7c012eef99da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:59.371219Z","signature_b64":"IfIuyy7UPM5W41Fw1eOczdp0TV3lzAv4w73evJ3tcrp6zeD2V/BalnBxJLu3s3uHZm9ELiROZDhRHiXXQxsMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5c56339cf14c903e42dc2056b3b2ff124c41990778d5b3b8e1c7c012eef99da","last_reissued_at":"2026-05-18T03:08:59.370643Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:59.370643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13049","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aUteRpvGUJ5Nw6zYz6CZ257Xa6J9/MF+KtXTsXOzHMhA0ktru3yX7W/03mvTJ8aSfvNxlgl2UVB2L50GONyiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:19:27.655072Z"},"content_sha256":"6511c4771ab862ac063524c360a25ca70e0efd1eebc3888b089a47117c097eb9","schema_version":"1.0","event_id":"sha256:6511c4771ab862ac063524c360a25ca70e0efd1eebc3888b089a47117c097eb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6XCWGOOPCTEQHZBNYICWWOZP6E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-aware Spatial-Frequency Registration and Fusion for Infrared and Visible Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SFRF uses uncertainty estimates and thermal consistency to prevent cumulative errors when registering and fusing unregistered infrared and visible images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyuan Xu, Jinyuan Liu, Jun Ma, Xingyuan Li, Xingyue Zhu, Yang Zou, Zhiying Jiang","submitted_at":"2026-05-13T06:12:46Z","abstract_excerpt":"Infrared and Visible Image Fusion (IVIF) has shown promise in visual tasks under challenging environments, but fusion under unregistered conditions faces inherent misalignments. Current studies to solve them either predict the deformation parameters coarse-to-fine (i.e., coarse registration and fine registration) or estimate the deformation fields in multi-scales for registration. Though straightforward, they overlook the cumulative errors in registration, which contaminate the fusion stage and severely deteriorate the resulting images. We introduce the Spatial-Frequency Registration and Fusio"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SFRF incorporates uncertainty estimation and infrared thermal radiation distribution consistency into a unified pipeline to handle the error accumulation for robust registration and fusion across both spatial and frequency domains.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That uncertainty estimates produced at each registration stage can be reliably used to prevent cumulative errors from contaminating the final fused image without introducing new artifacts or requiring extensive tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SFRF combines uncertainty-aware multi-scale registration with frequency-domain thermal consistency and dual-branch fusion to handle unregistered infrared-visible image pairs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SFRF uses uncertainty estimates and thermal consistency to prevent cumulative errors when registering and fusing unregistered infrared and visible images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4a2e00efe57bdfefc7f1219f5bada56c15e0d52f404a1044b92f7058594f5bc4"},"source":{"id":"2605.13049","kind":"arxiv","version":1},"verdict":{"id":"d24bcc3e-58a4-4eaa-a995-76cb4af27f8b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:28:07.943515Z","strongest_claim":"SFRF incorporates uncertainty estimation and infrared thermal radiation distribution consistency into a unified pipeline to handle the error accumulation for robust registration and fusion across both spatial and frequency domains.","one_line_summary":"SFRF combines uncertainty-aware multi-scale registration with frequency-domain thermal consistency and dual-branch fusion to handle unregistered infrared-visible image pairs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That uncertainty estimates produced at each registration stage can be reliably used to prevent cumulative errors from contaminating the final fused image without introducing new artifacts or requiring extensive tuning.","pith_extraction_headline":"SFRF uses uncertainty estimates and thermal consistency to prevent cumulative errors when registering and fusing unregistered infrared and visible images."},"references":{"count":43,"sample":[{"doi":"","year":2020,"title":"Unsupervised multi-modal im- age registration via geometry preserving image-to-image transla- tion","work_id":"5b59982a-5152-423b-8f02-25fde2f80561","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Refusion: Learning image fusion from reconstruction with learnable loss via meta-learning.International Journal of Com- puter Vision, pages 1–21,","work_id":"46e915dd-e3d7-416b-b738-3d4259e1beca","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1995,"title":"Beauchemin and John L","work_id":"324d23d5-a94e-4bb2-8e1a-d76bf208a962","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"Large displacement optical flow: descriptor matching in variational mo- tion estimation.IEEE transactions on pattern analysis and ma- chine intelligence, 33(3):500–513,","work_id":"4fd84e6d-ec9b-40df-b258-eab706bd9b0f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2000,"title":"Optical flow constraints on deformable models with applications to face tracking.International Journal of Computer Vision, 38(2):99–127,","work_id":"609995da-2abc-4ebd-8d1b-cb549ca1f8c0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":43,"snapshot_sha256":"dd9783c78d95256b10d09d82adc5e8bb2238bff95659de93fa059c099e59bf42","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"759fe7d2cdb4ccaafe304e6c9550af14c2d0c7dd2f7cbae81c267725904aca52"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d24bcc3e-58a4-4eaa-a995-76cb4af27f8b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qXQCd/iY8eF7Mhmvpe3uwl/CT/fN0eiyyTGmVdpO2mAjUadbayaQMTNCEE/XygW20Zjrb+tOj0+R7lf44xzbAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:19:27.655834Z"},"content_sha256":"cb3f1f68f7187a6c681bf8b631d45a45cb49720509911b9337b6fe811bf6efb6","schema_version":"1.0","event_id":"sha256:cb3f1f68f7187a6c681bf8b631d45a45cb49720509911b9337b6fe811bf6efb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XCWGOOPCTEQHZBNYICWWOZP6E/bundle.json","state_url":"https://pith.science/pith/6XCWGOOPCTEQHZBNYICWWOZP6E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XCWGOOPCTEQHZBNYICWWOZP6E/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T22:19:27Z","links":{"resolver":"https://pith.science/pith/6XCWGOOPCTEQHZBNYICWWOZP6E","bundle":"https://pith.science/pith/6XCWGOOPCTEQHZBNYICWWOZP6E/bundle.json","state":"https://pith.science/pith/6XCWGOOPCTEQHZBNYICWWOZP6E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XCWGOOPCTEQHZBNYICWWOZP6E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6XCWGOOPCTEQHZBNYICWWOZP6E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"034d636cd433ece28165d556b00860a79338f5eeba309e27ff61a6c16926b8a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T06:12:46Z","title_canon_sha256":"2a1c743aad3f0f166a19d2d3344a68c0ede573e1c3f56fe40fa96f9ca2e339b9"},"schema_version":"1.0","source":{"id":"2605.13049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13049","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13049v1","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13049","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"6XCWGOOPCTEQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6XCWGOOPCTEQHZBN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6XCWGOOP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:cb3f1f68f7187a6c681bf8b631d45a45cb49720509911b9337b6fe811bf6efb6","target":"graph","created_at":"2026-05-18T03:08:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"SFRF incorporates uncertainty estimation and infrared thermal radiation distribution consistency into a unified pipeline to handle the error accumulation for robust registration and fusion across both spatial and frequency domains."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That uncertainty estimates produced at each registration stage can be reliably used to prevent cumulative errors from contaminating the final fused image without introducing new artifacts or requiring extensive tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SFRF combines uncertainty-aware multi-scale registration with frequency-domain thermal consistency and dual-branch fusion to handle unregistered infrared-visible image pairs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SFRF uses uncertainty estimates and thermal consistency to prevent cumulative errors when registering and fusing unregistered infrared and visible images."}],"snapshot_sha256":"4a2e00efe57bdfefc7f1219f5bada56c15e0d52f404a1044b92f7058594f5bc4"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"759fe7d2cdb4ccaafe304e6c9550af14c2d0c7dd2f7cbae81c267725904aca52"},"paper":{"abstract_excerpt":"Infrared and Visible Image Fusion (IVIF) has shown promise in visual tasks under challenging environments, but fusion under unregistered conditions faces inherent misalignments. Current studies to solve them either predict the deformation parameters coarse-to-fine (i.e., coarse registration and fine registration) or estimate the deformation fields in multi-scales for registration. Though straightforward, they overlook the cumulative errors in registration, which contaminate the fusion stage and severely deteriorate the resulting images. We introduce the Spatial-Frequency Registration and Fusio","authors_text":"Haoyuan Xu, Jinyuan Liu, Jun Ma, Xingyuan Li, Xingyue Zhu, Yang Zou, Zhiying Jiang","cross_cats":[],"headline":"SFRF uses uncertainty estimates and thermal consistency to prevent cumulative errors when registering and fusing unregistered infrared and visible images.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T06:12:46Z","title":"Uncertainty-aware Spatial-Frequency Registration and Fusion for Infrared and Visible Images"},"references":{"count":43,"internal_anchors":0,"resolved_work":43,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Unsupervised multi-modal im- age registration via geometry preserving image-to-image transla- tion","work_id":"5b59982a-5152-423b-8f02-25fde2f80561","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Refusion: Learning image fusion from reconstruction with learnable loss via meta-learning.International Journal of Com- puter Vision, pages 1–21,","work_id":"46e915dd-e3d7-416b-b738-3d4259e1beca","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Beauchemin and John L","work_id":"324d23d5-a94e-4bb2-8e1a-d76bf208a962","year":1995},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Large displacement optical flow: descriptor matching in variational mo- tion estimation.IEEE transactions on pattern analysis and ma- chine intelligence, 33(3):500–513,","work_id":"4fd84e6d-ec9b-40df-b258-eab706bd9b0f","year":2010},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Optical flow constraints on deformable models with applications to face tracking.International Journal of Computer Vision, 38(2):99–127,","work_id":"609995da-2abc-4ebd-8d1b-cb549ca1f8c0","year":2000}],"snapshot_sha256":"dd9783c78d95256b10d09d82adc5e8bb2238bff95659de93fa059c099e59bf42"},"source":{"id":"2605.13049","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:28:07.943515Z","id":"d24bcc3e-58a4-4eaa-a995-76cb4af27f8b","model_set":{"reader":"grok-4.3"},"one_line_summary":"SFRF combines uncertainty-aware multi-scale registration with frequency-domain thermal consistency and dual-branch fusion to handle unregistered infrared-visible image pairs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SFRF uses uncertainty estimates and thermal consistency to prevent cumulative errors when registering and fusing unregistered infrared and visible images.","strongest_claim":"SFRF incorporates uncertainty estimation and infrared thermal radiation distribution consistency into a unified pipeline to handle the error accumulation for robust registration and fusion across both spatial and frequency domains.","weakest_assumption":"That uncertainty estimates produced at each registration stage can be reliably used to prevent cumulative errors from contaminating the final fused image without introducing new artifacts or requiring extensive tuning."}},"verdict_id":"d24bcc3e-58a4-4eaa-a995-76cb4af27f8b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6511c4771ab862ac063524c360a25ca70e0efd1eebc3888b089a47117c097eb9","target":"record","created_at":"2026-05-18T03:08:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"034d636cd433ece28165d556b00860a79338f5eeba309e27ff61a6c16926b8a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T06:12:46Z","title_canon_sha256":"2a1c743aad3f0f166a19d2d3344a68c0ede573e1c3f56fe40fa96f9ca2e339b9"},"schema_version":"1.0","source":{"id":"2605.13049","kind":"arxiv","version":1}},"canonical_sha256":"f5c56339cf14c903e42dc2056b3b2ff124c41990778d5b3b8e1c7c012eef99da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5c56339cf14c903e42dc2056b3b2ff124c41990778d5b3b8e1c7c012eef99da","first_computed_at":"2026-05-18T03:08:59.370643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:59.370643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IfIuyy7UPM5W41Fw1eOczdp0TV3lzAv4w73evJ3tcrp6zeD2V/BalnBxJLu3s3uHZm9ELiROZDhRHiXXQxsMCw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:59.371219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6511c4771ab862ac063524c360a25ca70e0efd1eebc3888b089a47117c097eb9","sha256:cb3f1f68f7187a6c681bf8b631d45a45cb49720509911b9337b6fe811bf6efb6"],"state_sha256":"289e58e4cf208fe2139e43f746c24847de3bdecd8cf53bdce0c55d22f2388bbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8dlU5nqIBst5z9Bmv2tCZDYabEuqKh5nJy0b9tLOiBWVpeH+MlrAB2dETkRg9GfNCBCv4DR6K3woTjA5lm9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T22:19:27.658969Z","bundle_sha256":"1d4f6702573811526a0992b3dfecdd85d3ec02f5c2aa35e46f9c3e1c913ede42"}}