{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I4B7DZ54LEBZQBRNDRYFIYWY3F","short_pith_number":"pith:I4B7DZ54","schema_version":"1.0","canonical_sha256":"4703f1e7bc590398062d1c705462d8d94edd39ef0c81584fb7cd86118104958e","source":{"kind":"arxiv","id":"2411.10309","version":2},"attestation_state":"computed","paper":{"title":"Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Siqi Jiang, Weidong Zhao, Wenlong Hou, Xianhui Liu, Xiao Lai, Ziqi Xie","submitted_at":"2024-11-15T16:05:01Z","abstract_excerpt":"Current image stitching methods often produce noticeable seams in challenging scenarios such as uneven hue and large parallax. To tackle this problem, we propose the Reference-Driven Inpainting Stitcher (RDIStitcher), which reformulates the image fusion and rectangling as a reference-based inpainting model, incorporating a larger modification fusion area and stronger modification intensity than previous methods. Furthermore, we introduce a self-supervised model training method, which enables the implementation of RDIStitcher without requiring labeled data by fine-tuning a Text-to-Image (T2I) d"},"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":"2411.10309","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T16:05:01Z","cross_cats_sorted":[],"title_canon_sha256":"51caf11382c71f8181a13111fb5bea8f522ba34fb4ef86de73223ce802095294","abstract_canon_sha256":"eb35f1e7ee0e1ec11556b32f10c6e682ae962496d20000dcf1854478ab6bcf18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:10.601655Z","signature_b64":"WwS1/gjap1nVt2bAX10x4kyTuJ78MbeQc5IeYny4BnCbqEQUWr+hIXs6EOay5S+MAV8G5gliw2LECBT3O0ybCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4703f1e7bc590398062d1c705462d8d94edd39ef0c81584fb7cd86118104958e","last_reissued_at":"2026-07-05T10:26:10.600710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:10.600710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Siqi Jiang, Weidong Zhao, Wenlong Hou, Xianhui Liu, Xiao Lai, Ziqi Xie","submitted_at":"2024-11-15T16:05:01Z","abstract_excerpt":"Current image stitching methods often produce noticeable seams in challenging scenarios such as uneven hue and large parallax. To tackle this problem, we propose the Reference-Driven Inpainting Stitcher (RDIStitcher), which reformulates the image fusion and rectangling as a reference-based inpainting model, incorporating a larger modification fusion area and stronger modification intensity than previous methods. Furthermore, we introduce a self-supervised model training method, which enables the implementation of RDIStitcher without requiring labeled data by fine-tuning a Text-to-Image (T2I) d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10309","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/2411.10309/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":"2411.10309","created_at":"2026-07-05T10:26:10.600832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10309v2","created_at":"2026-07-05T10:26:10.600832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10309","created_at":"2026-07-05T10:26:10.600832+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4B7DZ54LEBZ","created_at":"2026-07-05T10:26:10.600832+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4B7DZ54LEBZQBRN","created_at":"2026-07-05T10:26:10.600832+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4B7DZ54","created_at":"2026-07-05T10:26:10.600832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13041","citing_title":"SeamEdit: A Black-Box VLM-Agnostic Pipeline for Large-Image Semantic Editing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12575","citing_title":"StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4B7DZ54LEBZQBRNDRYFIYWY3F","json":"https://pith.science/pith/I4B7DZ54LEBZQBRNDRYFIYWY3F.json","graph_json":"https://pith.science/api/pith-number/I4B7DZ54LEBZQBRNDRYFIYWY3F/graph.json","events_json":"https://pith.science/api/pith-number/I4B7DZ54LEBZQBRNDRYFIYWY3F/events.json","paper":"https://pith.science/paper/I4B7DZ54"},"agent_actions":{"view_html":"https://pith.science/pith/I4B7DZ54LEBZQBRNDRYFIYWY3F","download_json":"https://pith.science/pith/I4B7DZ54LEBZQBRNDRYFIYWY3F.json","view_paper":"https://pith.science/paper/I4B7DZ54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10309&json=true","fetch_graph":"https://pith.science/api/pith-number/I4B7DZ54LEBZQBRNDRYFIYWY3F/graph.json","fetch_events":"https://pith.science/api/pith-number/I4B7DZ54LEBZQBRNDRYFIYWY3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4B7DZ54LEBZQBRNDRYFIYWY3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4B7DZ54LEBZQBRNDRYFIYWY3F/action/storage_attestation","attest_author":"https://pith.science/pith/I4B7DZ54LEBZQBRNDRYFIYWY3F/action/author_attestation","sign_citation":"https://pith.science/pith/I4B7DZ54LEBZQBRNDRYFIYWY3F/action/citation_signature","submit_replication":"https://pith.science/pith/I4B7DZ54LEBZQBRNDRYFIYWY3F/action/replication_record"}},"created_at":"2026-07-05T10:26:10.600832+00:00","updated_at":"2026-07-05T10:26:10.600832+00:00"}