{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3P3ZVH4CXMQSFW4QX4TA6CHI2E","short_pith_number":"pith:3P3ZVH4C","schema_version":"1.0","canonical_sha256":"dbf79a9f82bb2122db90bf260f08e8d1337efd619f0002368cb4dca96270c4ca","source":{"kind":"arxiv","id":"2301.05489","version":3},"attestation_state":"computed","paper":{"title":"A Residual Diffusion Model for High Perceptual Quality Codec Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Auke Wiggers, Guillaume Sauti\\`ere, Jens Petersen, Noor Fathima Ghouse, Tianlin Xu","submitted_at":"2023-01-13T11:27:26Z","abstract_excerpt":"Diffusion probabilistic models have recently achieved remarkable success in generating high quality image and video data. In this work, we build on this class of generative models and introduce a method for lossy compression of high resolution images. The resulting codec, which we call DIffuson-based Residual Augmentation Codec (DIRAC), is the first neural codec to allow smooth traversal of the rate-distortion-perception tradeoff at test time, while obtaining competitive performance with GAN-based methods in perceptual quality. Furthermore, while sampling from diffusion probabilistic models is"},"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":"2301.05489","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-13T11:27:26Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"da4e789aafdfbbd6e1d4932b1b2aac8163be0a842aede1cd5678a2204fdd2c57","abstract_canon_sha256":"79c44812152cf78e8d591585850325f91d256847849e31d7f0f753c14891fabb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:02.421968Z","signature_b64":"dUDbrqIyn2nTRx4VlXl+LUyvLOEFfDBnIJhat0if0eYZW/t1a5ukAKe8xH39Eptomi7Ez654tzznJ/AM0FAwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbf79a9f82bb2122db90bf260f08e8d1337efd619f0002368cb4dca96270c4ca","last_reissued_at":"2026-07-05T05:56:02.421376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:02.421376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Residual Diffusion Model for High Perceptual Quality Codec Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Auke Wiggers, Guillaume Sauti\\`ere, Jens Petersen, Noor Fathima Ghouse, Tianlin Xu","submitted_at":"2023-01-13T11:27:26Z","abstract_excerpt":"Diffusion probabilistic models have recently achieved remarkable success in generating high quality image and video data. In this work, we build on this class of generative models and introduce a method for lossy compression of high resolution images. The resulting codec, which we call DIffuson-based Residual Augmentation Codec (DIRAC), is the first neural codec to allow smooth traversal of the rate-distortion-perception tradeoff at test time, while obtaining competitive performance with GAN-based methods in perceptual quality. Furthermore, while sampling from diffusion probabilistic models is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05489","kind":"arxiv","version":3},"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/2301.05489/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":"2301.05489","created_at":"2026-07-05T05:56:02.421448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.05489v3","created_at":"2026-07-05T05:56:02.421448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05489","created_at":"2026-07-05T05:56:02.421448+00:00"},{"alias_kind":"pith_short_12","alias_value":"3P3ZVH4CXMQS","created_at":"2026-07-05T05:56:02.421448+00:00"},{"alias_kind":"pith_short_16","alias_value":"3P3ZVH4CXMQSFW4Q","created_at":"2026-07-05T05:56:02.421448+00:00"},{"alias_kind":"pith_short_8","alias_value":"3P3ZVH4C","created_at":"2026-07-05T05:56:02.421448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01608","citing_title":"Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10546","citing_title":"Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06568","citing_title":"A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3P3ZVH4CXMQSFW4QX4TA6CHI2E","json":"https://pith.science/pith/3P3ZVH4CXMQSFW4QX4TA6CHI2E.json","graph_json":"https://pith.science/api/pith-number/3P3ZVH4CXMQSFW4QX4TA6CHI2E/graph.json","events_json":"https://pith.science/api/pith-number/3P3ZVH4CXMQSFW4QX4TA6CHI2E/events.json","paper":"https://pith.science/paper/3P3ZVH4C"},"agent_actions":{"view_html":"https://pith.science/pith/3P3ZVH4CXMQSFW4QX4TA6CHI2E","download_json":"https://pith.science/pith/3P3ZVH4CXMQSFW4QX4TA6CHI2E.json","view_paper":"https://pith.science/paper/3P3ZVH4C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.05489&json=true","fetch_graph":"https://pith.science/api/pith-number/3P3ZVH4CXMQSFW4QX4TA6CHI2E/graph.json","fetch_events":"https://pith.science/api/pith-number/3P3ZVH4CXMQSFW4QX4TA6CHI2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3P3ZVH4CXMQSFW4QX4TA6CHI2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3P3ZVH4CXMQSFW4QX4TA6CHI2E/action/storage_attestation","attest_author":"https://pith.science/pith/3P3ZVH4CXMQSFW4QX4TA6CHI2E/action/author_attestation","sign_citation":"https://pith.science/pith/3P3ZVH4CXMQSFW4QX4TA6CHI2E/action/citation_signature","submit_replication":"https://pith.science/pith/3P3ZVH4CXMQSFW4QX4TA6CHI2E/action/replication_record"}},"created_at":"2026-07-05T05:56:02.421448+00:00","updated_at":"2026-07-05T05:56:02.421448+00:00"}