{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HTVEGABDFC3VLROOVCAQK7UGPG","short_pith_number":"pith:HTVEGABD","schema_version":"1.0","canonical_sha256":"3cea43002328b755c5cea881057e8679ac3fa0362c39a1cd6807bccc95b576c4","source":{"kind":"arxiv","id":"2503.18446","version":2},"attestation_state":"computed","paper":{"title":"Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinho Jeong, Jinwoo Kim, Sangmin Han, Seon Joo Kim","submitted_at":"2025-03-24T08:50:15Z","abstract_excerpt":"In this paper, we propose LSRNA, a novel framework for higher-resolution (exceeding 1K) image generation using diffusion models by leveraging super-resolution directly in the latent space. Existing diffusion models struggle with scaling beyond their training resolutions, often leading to structural distortions or content repetition. Reference-based methods address the issues by upsampling a low-resolution reference to guide higher-resolution generation. However, they face significant challenges: upsampling in latent space often causes manifold deviation, which degrades output quality. On the o"},"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":"2503.18446","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T08:50:15Z","cross_cats_sorted":[],"title_canon_sha256":"d0328f1d714369e08515678b30c1d749f2bd1ba43bed621ac90ac0250a2ba3ff","abstract_canon_sha256":"404c106801f08b762f357c7d0b2b350f26a7c9d9fc4b533af75397c792587bce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:46.116288Z","signature_b64":"v29uYfREMCHiE5xgoRI03QAiHaYk5CYnJs9mdXSQtV5vXwkvJU0YVj9TNVuhLUPNhOca1lAp5HRLV6dcICkZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cea43002328b755c5cea881057e8679ac3fa0362c39a1cd6807bccc95b576c4","last_reissued_at":"2026-07-05T10:38:46.115817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:46.115817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinho Jeong, Jinwoo Kim, Sangmin Han, Seon Joo Kim","submitted_at":"2025-03-24T08:50:15Z","abstract_excerpt":"In this paper, we propose LSRNA, a novel framework for higher-resolution (exceeding 1K) image generation using diffusion models by leveraging super-resolution directly in the latent space. Existing diffusion models struggle with scaling beyond their training resolutions, often leading to structural distortions or content repetition. Reference-based methods address the issues by upsampling a low-resolution reference to guide higher-resolution generation. However, they face significant challenges: upsampling in latent space often causes manifold deviation, which degrades output quality. On the o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18446","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/2503.18446/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":"2503.18446","created_at":"2026-07-05T10:38:46.115873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18446v2","created_at":"2026-07-05T10:38:46.115873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18446","created_at":"2026-07-05T10:38:46.115873+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTVEGABDFC3V","created_at":"2026-07-05T10:38:46.115873+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTVEGABDFC3VLROO","created_at":"2026-07-05T10:38:46.115873+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTVEGABD","created_at":"2026-07-05T10:38:46.115873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.00433","citing_title":"Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTVEGABDFC3VLROOVCAQK7UGPG","json":"https://pith.science/pith/HTVEGABDFC3VLROOVCAQK7UGPG.json","graph_json":"https://pith.science/api/pith-number/HTVEGABDFC3VLROOVCAQK7UGPG/graph.json","events_json":"https://pith.science/api/pith-number/HTVEGABDFC3VLROOVCAQK7UGPG/events.json","paper":"https://pith.science/paper/HTVEGABD"},"agent_actions":{"view_html":"https://pith.science/pith/HTVEGABDFC3VLROOVCAQK7UGPG","download_json":"https://pith.science/pith/HTVEGABDFC3VLROOVCAQK7UGPG.json","view_paper":"https://pith.science/paper/HTVEGABD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18446&json=true","fetch_graph":"https://pith.science/api/pith-number/HTVEGABDFC3VLROOVCAQK7UGPG/graph.json","fetch_events":"https://pith.science/api/pith-number/HTVEGABDFC3VLROOVCAQK7UGPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTVEGABDFC3VLROOVCAQK7UGPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTVEGABDFC3VLROOVCAQK7UGPG/action/storage_attestation","attest_author":"https://pith.science/pith/HTVEGABDFC3VLROOVCAQK7UGPG/action/author_attestation","sign_citation":"https://pith.science/pith/HTVEGABDFC3VLROOVCAQK7UGPG/action/citation_signature","submit_replication":"https://pith.science/pith/HTVEGABDFC3VLROOVCAQK7UGPG/action/replication_record"}},"created_at":"2026-07-05T10:38:46.115873+00:00","updated_at":"2026-07-05T10:38:46.115873+00:00"}