{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q7KKTL6QZYBG2A65BWAP76YTEC","short_pith_number":"pith:Q7KKTL6Q","schema_version":"1.0","canonical_sha256":"87d4a9afd0ce026d03dd0d80fffb1320bdbe528b8154fb9a9b80366294609ebb","source":{"kind":"arxiv","id":"2406.16476","version":1},"attestation_state":"computed","paper":{"title":"ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Jingwen He, Shuwei Shi, Wenbo Li, Yinqiang Zheng, Yuechen Zhang","submitted_at":"2024-06-24T09:28:21Z","abstract_excerpt":"Diffusion models excel at producing high-quality images; however, scaling to higher resolutions, such as 4K, often results in over-smoothed content, structural distortions, and repetitive patterns. To this end, we introduce ResMaster, a novel, training-free method that empowers resolution-limited diffusion models to generate high-quality images beyond resolution restrictions. Specifically, ResMaster leverages a low-resolution reference image created by a pre-trained diffusion model to provide structural and fine-grained guidance for crafting high-resolution images on a patch-by-patch basis. To"},"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":"2406.16476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T09:28:21Z","cross_cats_sorted":[],"title_canon_sha256":"f9c2e2706a6aebcad35f1f4f15b5694d11960adfe4f3874fb56bd2e6e476397e","abstract_canon_sha256":"334b73ea729bc65c4afa06e5a43d8051d7fcfa1d2da12f0ead0ddbf616e5a266"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:59.302784Z","signature_b64":"O/kRgV9CejzSS32eHlh5FDIry2xjFUpJzIaUwR4HPX+nOEAzskVS1CSmJ2tr6r2rxJZXntZwPO8jCLR84inYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87d4a9afd0ce026d03dd0d80fffb1320bdbe528b8154fb9a9b80366294609ebb","last_reissued_at":"2026-07-05T08:35:59.302346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:59.302346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Jingwen He, Shuwei Shi, Wenbo Li, Yinqiang Zheng, Yuechen Zhang","submitted_at":"2024-06-24T09:28:21Z","abstract_excerpt":"Diffusion models excel at producing high-quality images; however, scaling to higher resolutions, such as 4K, often results in over-smoothed content, structural distortions, and repetitive patterns. To this end, we introduce ResMaster, a novel, training-free method that empowers resolution-limited diffusion models to generate high-quality images beyond resolution restrictions. Specifically, ResMaster leverages a low-resolution reference image created by a pre-trained diffusion model to provide structural and fine-grained guidance for crafting high-resolution images on a patch-by-patch basis. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16476","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/2406.16476/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":"2406.16476","created_at":"2026-07-05T08:35:59.302404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16476v1","created_at":"2026-07-05T08:35:59.302404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16476","created_at":"2026-07-05T08:35:59.302404+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7KKTL6QZYBG","created_at":"2026-07-05T08:35:59.302404+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7KKTL6QZYBG2A65","created_at":"2026-07-05T08:35:59.302404+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7KKTL6Q","created_at":"2026-07-05T08:35:59.302404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.02537","citing_title":"RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21002","citing_title":"SURF: Signature-Retained Fast Video Generation","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7KKTL6QZYBG2A65BWAP76YTEC","json":"https://pith.science/pith/Q7KKTL6QZYBG2A65BWAP76YTEC.json","graph_json":"https://pith.science/api/pith-number/Q7KKTL6QZYBG2A65BWAP76YTEC/graph.json","events_json":"https://pith.science/api/pith-number/Q7KKTL6QZYBG2A65BWAP76YTEC/events.json","paper":"https://pith.science/paper/Q7KKTL6Q"},"agent_actions":{"view_html":"https://pith.science/pith/Q7KKTL6QZYBG2A65BWAP76YTEC","download_json":"https://pith.science/pith/Q7KKTL6QZYBG2A65BWAP76YTEC.json","view_paper":"https://pith.science/paper/Q7KKTL6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16476&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7KKTL6QZYBG2A65BWAP76YTEC/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7KKTL6QZYBG2A65BWAP76YTEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7KKTL6QZYBG2A65BWAP76YTEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7KKTL6QZYBG2A65BWAP76YTEC/action/storage_attestation","attest_author":"https://pith.science/pith/Q7KKTL6QZYBG2A65BWAP76YTEC/action/author_attestation","sign_citation":"https://pith.science/pith/Q7KKTL6QZYBG2A65BWAP76YTEC/action/citation_signature","submit_replication":"https://pith.science/pith/Q7KKTL6QZYBG2A65BWAP76YTEC/action/replication_record"}},"created_at":"2026-07-05T08:35:59.302404+00:00","updated_at":"2026-07-05T08:35:59.302404+00:00"}