{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BPUGDT7SSGRS66VE42L3K7KN56","short_pith_number":"pith:BPUGDT7S","schema_version":"1.0","canonical_sha256":"0be861cff291a32f7aa4e697b57d4def8ecaa4dc42797b725f79947c608a3069","source":{"kind":"arxiv","id":"2006.09965","version":3},"attestation_state":"computed","paper":{"title":"High-Fidelity Generative Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Eirikur Agustsson, Fabian Mentzer, George Toderici, Michael Tschannen","submitted_at":"2020-06-17T16:21:10Z","abstract_excerpt":"We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system. In particular, we investigate normalization layers, generator and discriminator architectures, training strategies, as well as perceptual losses. In contrast to previous work, i) we obtain visually pleasing reconstructions that are perceptually similar to the input, ii) we operate in a broad range of bitrates, and iii) our approach can be applied to high-resolution images. We bridge the gap between rate-distortion-perception theory and pr"},"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":"2006.09965","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-06-17T16:21:10Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"a9ce99752654a60045796f52c3ed3441aec4f0f8bdf3d48855ff2040ca2be63b","abstract_canon_sha256":"5cfdb972a401b8570887cd8b1c7480c9190bb0d8c0ec145b731ca294aa423737"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:28.101564Z","signature_b64":"1WQK66LuRlgWpraPwlsRc9vZ6/B7vBqYk3ZWDTFBrvoqEQIq/gIudkMFYWtzmRWor+sUPOj4Ha103N7myPgaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0be861cff291a32f7aa4e697b57d4def8ecaa4dc42797b725f79947c608a3069","last_reissued_at":"2026-07-05T01:45:28.101149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:28.101149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Fidelity Generative Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Eirikur Agustsson, Fabian Mentzer, George Toderici, Michael Tschannen","submitted_at":"2020-06-17T16:21:10Z","abstract_excerpt":"We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system. In particular, we investigate normalization layers, generator and discriminator architectures, training strategies, as well as perceptual losses. In contrast to previous work, i) we obtain visually pleasing reconstructions that are perceptually similar to the input, ii) we operate in a broad range of bitrates, and iii) our approach can be applied to high-resolution images. We bridge the gap between rate-distortion-perception theory and pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09965","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/2006.09965/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":"2006.09965","created_at":"2026-07-05T01:45:28.101205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09965v3","created_at":"2026-07-05T01:45:28.101205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09965","created_at":"2026-07-05T01:45:28.101205+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPUGDT7SSGRS","created_at":"2026-07-05T01:45:28.101205+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPUGDT7SSGRS66VE","created_at":"2026-07-05T01:45:28.101205+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPUGDT7S","created_at":"2026-07-05T01:45:28.101205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26398","citing_title":"DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22371","citing_title":"ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13366","citing_title":"Dual-Constrained Diffusion Image Compression for Operational Rate-Distortion-Perception Optimization","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26398","citing_title":"DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00635","citing_title":"How Neural Losses Shape VAE Latents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26571","citing_title":"GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPUGDT7SSGRS66VE42L3K7KN56","json":"https://pith.science/pith/BPUGDT7SSGRS66VE42L3K7KN56.json","graph_json":"https://pith.science/api/pith-number/BPUGDT7SSGRS66VE42L3K7KN56/graph.json","events_json":"https://pith.science/api/pith-number/BPUGDT7SSGRS66VE42L3K7KN56/events.json","paper":"https://pith.science/paper/BPUGDT7S"},"agent_actions":{"view_html":"https://pith.science/pith/BPUGDT7SSGRS66VE42L3K7KN56","download_json":"https://pith.science/pith/BPUGDT7SSGRS66VE42L3K7KN56.json","view_paper":"https://pith.science/paper/BPUGDT7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09965&json=true","fetch_graph":"https://pith.science/api/pith-number/BPUGDT7SSGRS66VE42L3K7KN56/graph.json","fetch_events":"https://pith.science/api/pith-number/BPUGDT7SSGRS66VE42L3K7KN56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPUGDT7SSGRS66VE42L3K7KN56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPUGDT7SSGRS66VE42L3K7KN56/action/storage_attestation","attest_author":"https://pith.science/pith/BPUGDT7SSGRS66VE42L3K7KN56/action/author_attestation","sign_citation":"https://pith.science/pith/BPUGDT7SSGRS66VE42L3K7KN56/action/citation_signature","submit_replication":"https://pith.science/pith/BPUGDT7SSGRS66VE42L3K7KN56/action/replication_record"}},"created_at":"2026-07-05T01:45:28.101205+00:00","updated_at":"2026-07-05T01:45:28.101205+00:00"}