{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:54A7CTI656SH7ZLAB7GXAJCMXI","short_pith_number":"pith:54A7CTI6","schema_version":"1.0","canonical_sha256":"ef01f14d1eefa47fe5600fcd70244cba0bde3d622bb2081fad24c6f32fac0b27","source":{"kind":"arxiv","id":"2305.17105","version":1},"attestation_state":"computed","paper":{"title":"Random-Access Neural Compression of Material Textures","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Aaron Lefohn, Bartlomiej Wronski, Karthik Vaidyanathan, Marco Salvi, Pontus Ebelin, Tomas Akenine-M\\\"oller","submitted_at":"2023-05-26T17:16:22Z","abstract_excerpt":"The continuous advancement of photorealism in rendering is accompanied by a growth in texture data and, consequently, increasing storage and memory demands. To address this issue, we propose a novel neural compression technique specifically designed for material textures. We unlock two more levels of detail, i.e., 16x more texels, using low bitrate compression, with image quality that is better than advanced image compression techniques, such as AVIF and JPEG XL. At the same time, our method allows on-demand, real-time decompression with random access similar to block texture compression on GP"},"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":"2305.17105","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.GR","submitted_at":"2023-05-26T17:16:22Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1d800322b707385e09659d83f73951df70746be002e44e47841db695acf8fbee","abstract_canon_sha256":"e173c7f0c88ba0d54bc3dfd126dbf1c2d49ababc76229b10dc6eb55f670713ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:09.238521Z","signature_b64":"+0hHx5XEyujy8W65FSZOIYWAc20d6MdYjhB9ZUZXdy9xa0c6b4T+mnfFT2tQr2er1pDFJ9XuKvuuDXE5Ig+MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef01f14d1eefa47fe5600fcd70244cba0bde3d622bb2081fad24c6f32fac0b27","last_reissued_at":"2026-07-05T06:35:09.238031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:09.238031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random-Access Neural Compression of Material Textures","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Aaron Lefohn, Bartlomiej Wronski, Karthik Vaidyanathan, Marco Salvi, Pontus Ebelin, Tomas Akenine-M\\\"oller","submitted_at":"2023-05-26T17:16:22Z","abstract_excerpt":"The continuous advancement of photorealism in rendering is accompanied by a growth in texture data and, consequently, increasing storage and memory demands. To address this issue, we propose a novel neural compression technique specifically designed for material textures. We unlock two more levels of detail, i.e., 16x more texels, using low bitrate compression, with image quality that is better than advanced image compression techniques, such as AVIF and JPEG XL. At the same time, our method allows on-demand, real-time decompression with random access similar to block texture compression on GP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17105","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/2305.17105/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":"2305.17105","created_at":"2026-07-05T06:35:09.238094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17105v1","created_at":"2026-07-05T06:35:09.238094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17105","created_at":"2026-07-05T06:35:09.238094+00:00"},{"alias_kind":"pith_short_12","alias_value":"54A7CTI656SH","created_at":"2026-07-05T06:35:09.238094+00:00"},{"alias_kind":"pith_short_16","alias_value":"54A7CTI656SH7ZLA","created_at":"2026-07-05T06:35:09.238094+00:00"},{"alias_kind":"pith_short_8","alias_value":"54A7CTI6","created_at":"2026-07-05T06:35:09.238094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21984","citing_title":"Soft Anisotropic Diagrams for Differentiable Image Representation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54A7CTI656SH7ZLAB7GXAJCMXI","json":"https://pith.science/pith/54A7CTI656SH7ZLAB7GXAJCMXI.json","graph_json":"https://pith.science/api/pith-number/54A7CTI656SH7ZLAB7GXAJCMXI/graph.json","events_json":"https://pith.science/api/pith-number/54A7CTI656SH7ZLAB7GXAJCMXI/events.json","paper":"https://pith.science/paper/54A7CTI6"},"agent_actions":{"view_html":"https://pith.science/pith/54A7CTI656SH7ZLAB7GXAJCMXI","download_json":"https://pith.science/pith/54A7CTI656SH7ZLAB7GXAJCMXI.json","view_paper":"https://pith.science/paper/54A7CTI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17105&json=true","fetch_graph":"https://pith.science/api/pith-number/54A7CTI656SH7ZLAB7GXAJCMXI/graph.json","fetch_events":"https://pith.science/api/pith-number/54A7CTI656SH7ZLAB7GXAJCMXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54A7CTI656SH7ZLAB7GXAJCMXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54A7CTI656SH7ZLAB7GXAJCMXI/action/storage_attestation","attest_author":"https://pith.science/pith/54A7CTI656SH7ZLAB7GXAJCMXI/action/author_attestation","sign_citation":"https://pith.science/pith/54A7CTI656SH7ZLAB7GXAJCMXI/action/citation_signature","submit_replication":"https://pith.science/pith/54A7CTI656SH7ZLAB7GXAJCMXI/action/replication_record"}},"created_at":"2026-07-05T06:35:09.238094+00:00","updated_at":"2026-07-05T06:35:09.238094+00:00"}