{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M2EL6VLMWAS7B44G5NCZYF75SN","short_pith_number":"pith:M2EL6VLM","schema_version":"1.0","canonical_sha256":"6688bf556cb025f0f386eb459c17fd937268b1369d042b5ed3f240f4075631ce","source":{"kind":"arxiv","id":"2404.18820","version":4},"attestation_state":"computed","paper":{"title":"Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chenyang Ge, Hao Wei, Jingwen Jiang, Yanhui Zhou, Zhiyuan Li","submitted_at":"2024-04-29T16:02:38Z","abstract_excerpt":"Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the powerful generative capability of pre-trained diffusion models to achieve realistic image reconstruction at extremely low bitrates. In the first stage, we treat the latent representation of images in the diffusion space as guidance, employing a VAE-based compression approach to compress images and initially decode the compressed information into content variab"},"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":"2404.18820","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2024-04-29T16:02:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4986ab6938308d850850ee2ff2df36022597117009910207e6e6b3bf37afed0c","abstract_canon_sha256":"597193d245e49b42bcf95093ec895bc173ea053fcd7d1fd642dcf2c4159be4a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:58.059280Z","signature_b64":"O8rX1Y6lXU6n+3umryYiQ181lXkO/Z/5lvRCGlaD5aSooPGyTxYoxxWMujFnFO76+JPdC2czPixZwJPUmHnZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6688bf556cb025f0f386eb459c17fd937268b1369d042b5ed3f240f4075631ce","last_reissued_at":"2026-07-05T09:02:58.058796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:58.058796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chenyang Ge, Hao Wei, Jingwen Jiang, Yanhui Zhou, Zhiyuan Li","submitted_at":"2024-04-29T16:02:38Z","abstract_excerpt":"Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the powerful generative capability of pre-trained diffusion models to achieve realistic image reconstruction at extremely low bitrates. In the first stage, we treat the latent representation of images in the diffusion space as guidance, employing a VAE-based compression approach to compress images and initially decode the compressed information into content variab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18820","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/2404.18820/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":"2404.18820","created_at":"2026-07-05T09:02:58.058861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18820v4","created_at":"2026-07-05T09:02:58.058861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18820","created_at":"2026-07-05T09:02:58.058861+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2EL6VLMWAS7","created_at":"2026-07-05T09:02:58.058861+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2EL6VLMWAS7B44G","created_at":"2026-07-05T09:02:58.058861+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2EL6VLM","created_at":"2026-07-05T09:02:58.058861+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/M2EL6VLMWAS7B44G5NCZYF75SN","json":"https://pith.science/pith/M2EL6VLMWAS7B44G5NCZYF75SN.json","graph_json":"https://pith.science/api/pith-number/M2EL6VLMWAS7B44G5NCZYF75SN/graph.json","events_json":"https://pith.science/api/pith-number/M2EL6VLMWAS7B44G5NCZYF75SN/events.json","paper":"https://pith.science/paper/M2EL6VLM"},"agent_actions":{"view_html":"https://pith.science/pith/M2EL6VLMWAS7B44G5NCZYF75SN","download_json":"https://pith.science/pith/M2EL6VLMWAS7B44G5NCZYF75SN.json","view_paper":"https://pith.science/paper/M2EL6VLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18820&json=true","fetch_graph":"https://pith.science/api/pith-number/M2EL6VLMWAS7B44G5NCZYF75SN/graph.json","fetch_events":"https://pith.science/api/pith-number/M2EL6VLMWAS7B44G5NCZYF75SN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2EL6VLMWAS7B44G5NCZYF75SN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2EL6VLMWAS7B44G5NCZYF75SN/action/storage_attestation","attest_author":"https://pith.science/pith/M2EL6VLMWAS7B44G5NCZYF75SN/action/author_attestation","sign_citation":"https://pith.science/pith/M2EL6VLMWAS7B44G5NCZYF75SN/action/citation_signature","submit_replication":"https://pith.science/pith/M2EL6VLMWAS7B44G5NCZYF75SN/action/replication_record"}},"created_at":"2026-07-05T09:02:58.058861+00:00","updated_at":"2026-07-05T09:02:58.058861+00:00"}