{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GDFIZ4UIXDLX2LLMNWNUR4QX3Z","short_pith_number":"pith:GDFIZ4UI","schema_version":"1.0","canonical_sha256":"30ca8cf288b8d77d2d6c6d9b48f217de647d6af17caf2e660136a8d19c2c48a1","source":{"kind":"arxiv","id":"2404.19475","version":4},"attestation_state":"computed","paper":{"title":"TwinDiffusion: Enhancing Coherence and Efficiency in Panoramic Image Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Teng Zhou, Yongchuan Tang","submitted_at":"2024-04-30T11:43:37Z","abstract_excerpt":"Diffusion models have emerged as effective tools for generating diverse and high-quality content. However, their capability in high-resolution image generation, particularly for panoramic images, still faces challenges such as visible seams and incoherent transitions. In this paper, we propose TwinDiffusion, an optimized framework designed to address these challenges through two key innovations: the Crop Fusion for quality enhancement and the Cross Sampling for efficiency optimization. We introduce a training-free optimizing stage to refine the similarity of adjacent image areas, as well as an"},"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":"2404.19475","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T11:43:37Z","cross_cats_sorted":[],"title_canon_sha256":"659b055448332e0c817bd147a5bc39b543ff37a914f5b51c51285823a0aa5fbf","abstract_canon_sha256":"672257c0227a6a13cf812643c47df63e107748d47236dbe7f3940888e3c5e88e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:02.354076Z","signature_b64":"ulOf8HEmzSeMtyhCsKUc+Y8j23kky19SqjZYIwkM6hcpmxf40t0LxJML4pqhb7lV2nf37z6Z9/irs+sX/gdWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30ca8cf288b8d77d2d6c6d9b48f217de647d6af17caf2e660136a8d19c2c48a1","last_reissued_at":"2026-07-05T08:41:02.353583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:02.353583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TwinDiffusion: Enhancing Coherence and Efficiency in Panoramic Image Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Teng Zhou, Yongchuan Tang","submitted_at":"2024-04-30T11:43:37Z","abstract_excerpt":"Diffusion models have emerged as effective tools for generating diverse and high-quality content. However, their capability in high-resolution image generation, particularly for panoramic images, still faces challenges such as visible seams and incoherent transitions. In this paper, we propose TwinDiffusion, an optimized framework designed to address these challenges through two key innovations: the Crop Fusion for quality enhancement and the Cross Sampling for efficiency optimization. We introduce a training-free optimizing stage to refine the similarity of adjacent image areas, as well as an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19475","kind":"arxiv","version":4},"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/2404.19475/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":"2404.19475","created_at":"2026-07-05T08:41:02.353647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19475v4","created_at":"2026-07-05T08:41:02.353647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19475","created_at":"2026-07-05T08:41:02.353647+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDFIZ4UIXDLX","created_at":"2026-07-05T08:41:02.353647+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDFIZ4UIXDLX2LLM","created_at":"2026-07-05T08:41:02.353647+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDFIZ4UI","created_at":"2026-07-05T08:41:02.353647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.00756","citing_title":"LeakyCLIP: Extracting Training Data from CLIP","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08309","citing_title":"InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDFIZ4UIXDLX2LLMNWNUR4QX3Z","json":"https://pith.science/pith/GDFIZ4UIXDLX2LLMNWNUR4QX3Z.json","graph_json":"https://pith.science/api/pith-number/GDFIZ4UIXDLX2LLMNWNUR4QX3Z/graph.json","events_json":"https://pith.science/api/pith-number/GDFIZ4UIXDLX2LLMNWNUR4QX3Z/events.json","paper":"https://pith.science/paper/GDFIZ4UI"},"agent_actions":{"view_html":"https://pith.science/pith/GDFIZ4UIXDLX2LLMNWNUR4QX3Z","download_json":"https://pith.science/pith/GDFIZ4UIXDLX2LLMNWNUR4QX3Z.json","view_paper":"https://pith.science/paper/GDFIZ4UI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19475&json=true","fetch_graph":"https://pith.science/api/pith-number/GDFIZ4UIXDLX2LLMNWNUR4QX3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/GDFIZ4UIXDLX2LLMNWNUR4QX3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDFIZ4UIXDLX2LLMNWNUR4QX3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDFIZ4UIXDLX2LLMNWNUR4QX3Z/action/storage_attestation","attest_author":"https://pith.science/pith/GDFIZ4UIXDLX2LLMNWNUR4QX3Z/action/author_attestation","sign_citation":"https://pith.science/pith/GDFIZ4UIXDLX2LLMNWNUR4QX3Z/action/citation_signature","submit_replication":"https://pith.science/pith/GDFIZ4UIXDLX2LLMNWNUR4QX3Z/action/replication_record"}},"created_at":"2026-07-05T08:41:02.353647+00:00","updated_at":"2026-07-05T08:41:02.353647+00:00"}