{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QYM5FJ4QQGUPLTPW3LYALBXYKL","short_pith_number":"pith:QYM5FJ4Q","schema_version":"1.0","canonical_sha256":"8619d2a79081a8f5cdf6daf00586f852f5b9c92d2c9e9858963d3476d821b01e","source":{"kind":"arxiv","id":"2412.00156","version":4},"attestation_state":"computed","paper":{"title":"VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jong Chul Ye, Taesung Kwon","submitted_at":"2024-11-29T08:10:49Z","abstract_excerpt":"In this paper, we propose a novel framework for solving high-definition video inverse problems using latent image diffusion models. Building on recent advancements in spatio-temporal optimization for video inverse problems using image diffusion models, our approach leverages latent-space diffusion models to achieve enhanced video quality and resolution. To address the high computational demands of processing high-resolution frames, we introduce a pseudo-batch consistent sampling strategy, allowing efficient operation on a single GPU. Additionally, to improve temporal consistency, we present ps"},"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":"2412.00156","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T08:10:49Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"0a8f8738226925d7da4f7a4886a39a92bf2df7df78f058d654c9901cecf4b3ef","abstract_canon_sha256":"3bdb9e1980b3878166cb5a4df230013c4d929efb03af3cf18649affd7de00ba0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:11.347342Z","signature_b64":"ScAPdSAP3ekyAWbN6yfF21PyfjMXLdhSrA/WxuIr9hEvP+NJ7zkTg1pZrZGr80Wl5fjPuEL/V+GTt1wru4qADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8619d2a79081a8f5cdf6daf00586f852f5b9c92d2c9e9858963d3476d821b01e","last_reissued_at":"2026-07-05T10:26:11.346793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:11.346793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jong Chul Ye, Taesung Kwon","submitted_at":"2024-11-29T08:10:49Z","abstract_excerpt":"In this paper, we propose a novel framework for solving high-definition video inverse problems using latent image diffusion models. Building on recent advancements in spatio-temporal optimization for video inverse problems using image diffusion models, our approach leverages latent-space diffusion models to achieve enhanced video quality and resolution. To address the high computational demands of processing high-resolution frames, we introduce a pseudo-batch consistent sampling strategy, allowing efficient operation on a single GPU. Additionally, to improve temporal consistency, we present ps"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00156","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/2412.00156/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":"2412.00156","created_at":"2026-07-05T10:26:11.346845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00156v4","created_at":"2026-07-05T10:26:11.346845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00156","created_at":"2026-07-05T10:26:11.346845+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYM5FJ4QQGUP","created_at":"2026-07-05T10:26:11.346845+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYM5FJ4QQGUPLTPW","created_at":"2026-07-05T10:26:11.346845+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYM5FJ4Q","created_at":"2026-07-05T10:26:11.346845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QYM5FJ4QQGUPLTPW3LYALBXYKL","json":"https://pith.science/pith/QYM5FJ4QQGUPLTPW3LYALBXYKL.json","graph_json":"https://pith.science/api/pith-number/QYM5FJ4QQGUPLTPW3LYALBXYKL/graph.json","events_json":"https://pith.science/api/pith-number/QYM5FJ4QQGUPLTPW3LYALBXYKL/events.json","paper":"https://pith.science/paper/QYM5FJ4Q"},"agent_actions":{"view_html":"https://pith.science/pith/QYM5FJ4QQGUPLTPW3LYALBXYKL","download_json":"https://pith.science/pith/QYM5FJ4QQGUPLTPW3LYALBXYKL.json","view_paper":"https://pith.science/paper/QYM5FJ4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00156&json=true","fetch_graph":"https://pith.science/api/pith-number/QYM5FJ4QQGUPLTPW3LYALBXYKL/graph.json","fetch_events":"https://pith.science/api/pith-number/QYM5FJ4QQGUPLTPW3LYALBXYKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYM5FJ4QQGUPLTPW3LYALBXYKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYM5FJ4QQGUPLTPW3LYALBXYKL/action/storage_attestation","attest_author":"https://pith.science/pith/QYM5FJ4QQGUPLTPW3LYALBXYKL/action/author_attestation","sign_citation":"https://pith.science/pith/QYM5FJ4QQGUPLTPW3LYALBXYKL/action/citation_signature","submit_replication":"https://pith.science/pith/QYM5FJ4QQGUPLTPW3LYALBXYKL/action/replication_record"}},"created_at":"2026-07-05T10:26:11.346845+00:00","updated_at":"2026-07-05T10:26:11.346845+00:00"}