{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PJ4EELC6F23BH7GC6DOWHUQSIT","short_pith_number":"pith:PJ4EELC6","schema_version":"1.0","canonical_sha256":"7a78422c5e2eb613fcc2f0dd63d21244d926cc482eb439d5a24631f210296b12","source":{"kind":"arxiv","id":"2508.07682","version":1},"attestation_state":"computed","paper":{"title":"DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Wenzhuo Ma, Zhenzhong Chen","submitted_at":"2025-08-11T06:59:23Z","abstract_excerpt":"In this work, we first propose DiffVC-OSD, a One-Step Diffusion-based Perceptual Neural Video Compression framework. Unlike conventional multi-step diffusion-based methods, DiffVC-OSD feeds the reconstructed latent representation directly into a One-Step Diffusion Model, enhancing perceptual quality through a single diffusion step guided by both temporal context and the latent itself. To better leverage temporal dependencies, we design a Temporal Context Adapter that encodes conditional inputs into multi-level features, offering more fine-grained guidance for the Denoising Unet. Additionally, "},"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":"2508.07682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-08-11T06:59:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e2c7f2b6fc3247a81e0415ca23c1fd1d5cab26b7836e7b574c787cede7a217cc","abstract_canon_sha256":"304f6574c4e0830d2f2d67579973eb3773149b1470c58da957dd3a08cdc4e974"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:04.723633Z","signature_b64":"0wwW9unfGf+fTdXQnAeJ2u0GRAq7d+ppzOlaO/qJApln80C0qjiBM6gy+a3vzQYPLx7bt3utNEHwBu3rxUvlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a78422c5e2eb613fcc2f0dd63d21244d926cc482eb439d5a24631f210296b12","last_reissued_at":"2026-07-05T11:52:04.723138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:04.723138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Wenzhuo Ma, Zhenzhong Chen","submitted_at":"2025-08-11T06:59:23Z","abstract_excerpt":"In this work, we first propose DiffVC-OSD, a One-Step Diffusion-based Perceptual Neural Video Compression framework. Unlike conventional multi-step diffusion-based methods, DiffVC-OSD feeds the reconstructed latent representation directly into a One-Step Diffusion Model, enhancing perceptual quality through a single diffusion step guided by both temporal context and the latent itself. To better leverage temporal dependencies, we design a Temporal Context Adapter that encodes conditional inputs into multi-level features, offering more fine-grained guidance for the Denoising Unet. Additionally, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07682","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/2508.07682/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":"2508.07682","created_at":"2026-07-05T11:52:04.723197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07682v1","created_at":"2026-07-05T11:52:04.723197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07682","created_at":"2026-07-05T11:52:04.723197+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJ4EELC6F23B","created_at":"2026-07-05T11:52:04.723197+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJ4EELC6F23BH7GC","created_at":"2026-07-05T11:52:04.723197+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJ4EELC6","created_at":"2026-07-05T11:52:04.723197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22371","citing_title":"ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13837","citing_title":"A Causal Diffusion Model for Video Reconstruction from Ultra-Low-Bitrate Representations","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJ4EELC6F23BH7GC6DOWHUQSIT","json":"https://pith.science/pith/PJ4EELC6F23BH7GC6DOWHUQSIT.json","graph_json":"https://pith.science/api/pith-number/PJ4EELC6F23BH7GC6DOWHUQSIT/graph.json","events_json":"https://pith.science/api/pith-number/PJ4EELC6F23BH7GC6DOWHUQSIT/events.json","paper":"https://pith.science/paper/PJ4EELC6"},"agent_actions":{"view_html":"https://pith.science/pith/PJ4EELC6F23BH7GC6DOWHUQSIT","download_json":"https://pith.science/pith/PJ4EELC6F23BH7GC6DOWHUQSIT.json","view_paper":"https://pith.science/paper/PJ4EELC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07682&json=true","fetch_graph":"https://pith.science/api/pith-number/PJ4EELC6F23BH7GC6DOWHUQSIT/graph.json","fetch_events":"https://pith.science/api/pith-number/PJ4EELC6F23BH7GC6DOWHUQSIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJ4EELC6F23BH7GC6DOWHUQSIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJ4EELC6F23BH7GC6DOWHUQSIT/action/storage_attestation","attest_author":"https://pith.science/pith/PJ4EELC6F23BH7GC6DOWHUQSIT/action/author_attestation","sign_citation":"https://pith.science/pith/PJ4EELC6F23BH7GC6DOWHUQSIT/action/citation_signature","submit_replication":"https://pith.science/pith/PJ4EELC6F23BH7GC6DOWHUQSIT/action/replication_record"}},"created_at":"2026-07-05T11:52:04.723197+00:00","updated_at":"2026-07-05T11:52:04.723197+00:00"}