{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3EPFTWWUBHMUHQYPF6VPBGEHDV","short_pith_number":"pith:3EPFTWWU","schema_version":"1.0","canonical_sha256":"d91e59dad409d943c30f2faaf098871d789222b82d190e3f873c2fa99a37bc98","source":{"kind":"arxiv","id":"2504.04658","version":1},"attestation_state":"computed","paper":{"title":"3DM-WeConvene: Learned Image Compression with 3D Multi-Level Wavelet-Domain Convolution and Entropy Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.CV","authors_text":"Feng Liang, Guohe Zhang, Haisheng Fu, Jie Liang, Jingning Han, Zhenman Fang","submitted_at":"2025-04-07T01:11:50Z","abstract_excerpt":"Learned image compression (LIC) has recently made significant progress, surpassing traditional methods. However, most LIC approaches operate mainly in the spatial domain and lack mechanisms for reducing frequency-domain correlations. To address this, we propose a novel framework that integrates low-complexity 3D multi-level Discrete Wavelet Transform (DWT) into convolutional layers and entropy coding, reducing both spatial and channel correlations to improve frequency selectivity and rate-distortion (R-D) performance.\n  Our proposed 3D multi-level wavelet-domain convolution (3DM-WeConv) layer "},"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":"2504.04658","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T01:11:50Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"edbfd198b5e8e9cb8d3f2c7023f8a9d93233001588c5c753cad4569c4633172f","abstract_canon_sha256":"1645af5fb9498920101f479d219ffa2b0679a5e1c8ab07cd1a130c8873fa8eee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:27.836523Z","signature_b64":"ZwGZWh4NevQyHJpIGhmJ0SalH7RyywK2hPBNNTCk2YzsyyVTQzWjrOj0lVfqMz0MsXwTK4yOJIC56e3SlwSlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d91e59dad409d943c30f2faaf098871d789222b82d190e3f873c2fa99a37bc98","last_reissued_at":"2026-07-05T10:45:27.836039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:27.836039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3DM-WeConvene: Learned Image Compression with 3D Multi-Level Wavelet-Domain Convolution and Entropy Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.CV","authors_text":"Feng Liang, Guohe Zhang, Haisheng Fu, Jie Liang, Jingning Han, Zhenman Fang","submitted_at":"2025-04-07T01:11:50Z","abstract_excerpt":"Learned image compression (LIC) has recently made significant progress, surpassing traditional methods. However, most LIC approaches operate mainly in the spatial domain and lack mechanisms for reducing frequency-domain correlations. To address this, we propose a novel framework that integrates low-complexity 3D multi-level Discrete Wavelet Transform (DWT) into convolutional layers and entropy coding, reducing both spatial and channel correlations to improve frequency selectivity and rate-distortion (R-D) performance.\n  Our proposed 3D multi-level wavelet-domain convolution (3DM-WeConv) layer "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04658","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/2504.04658/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":"2504.04658","created_at":"2026-07-05T10:45:27.836097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04658v1","created_at":"2026-07-05T10:45:27.836097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04658","created_at":"2026-07-05T10:45:27.836097+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EPFTWWUBHMU","created_at":"2026-07-05T10:45:27.836097+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EPFTWWUBHMUHQYP","created_at":"2026-07-05T10:45:27.836097+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EPFTWWU","created_at":"2026-07-05T10:45:27.836097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00111","citing_title":"ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3EPFTWWUBHMUHQYPF6VPBGEHDV","json":"https://pith.science/pith/3EPFTWWUBHMUHQYPF6VPBGEHDV.json","graph_json":"https://pith.science/api/pith-number/3EPFTWWUBHMUHQYPF6VPBGEHDV/graph.json","events_json":"https://pith.science/api/pith-number/3EPFTWWUBHMUHQYPF6VPBGEHDV/events.json","paper":"https://pith.science/paper/3EPFTWWU"},"agent_actions":{"view_html":"https://pith.science/pith/3EPFTWWUBHMUHQYPF6VPBGEHDV","download_json":"https://pith.science/pith/3EPFTWWUBHMUHQYPF6VPBGEHDV.json","view_paper":"https://pith.science/paper/3EPFTWWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04658&json=true","fetch_graph":"https://pith.science/api/pith-number/3EPFTWWUBHMUHQYPF6VPBGEHDV/graph.json","fetch_events":"https://pith.science/api/pith-number/3EPFTWWUBHMUHQYPF6VPBGEHDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EPFTWWUBHMUHQYPF6VPBGEHDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EPFTWWUBHMUHQYPF6VPBGEHDV/action/storage_attestation","attest_author":"https://pith.science/pith/3EPFTWWUBHMUHQYPF6VPBGEHDV/action/author_attestation","sign_citation":"https://pith.science/pith/3EPFTWWUBHMUHQYPF6VPBGEHDV/action/citation_signature","submit_replication":"https://pith.science/pith/3EPFTWWUBHMUHQYPF6VPBGEHDV/action/replication_record"}},"created_at":"2026-07-05T10:45:27.836097+00:00","updated_at":"2026-07-05T10:45:27.836097+00:00"}