{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:APJNJ4TI72OBV7MTNRKHYHBDIQ","short_pith_number":"pith:APJNJ4TI","schema_version":"1.0","canonical_sha256":"03d2d4f268fe9c1afd936c547c1c23443803bcf1973dbeac715ffd731879db4d","source":{"kind":"arxiv","id":"2312.05915","version":2},"attestation_state":"computed","paper":{"title":"Diffusion for Natural Image Matting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Humphrey Shi, Wei Wang, Yao Zhao, Yihan Hu, Yiheng Lin, Yunchao Wei","submitted_at":"2023-12-10T15:28:56Z","abstract_excerpt":"We aim to leverage diffusion to address the challenging image matting task. However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles to achieving this goal. In this paper, we present DiffMatte, a solution designed to effectively overcome these challenges. First, DiffMatte decouples the decoder from the intricately coupled matting network design, involving only one lightweight decoder in the iterations of the diffusion process. With such a strategy, DiffMatte mitigates the growth of compu"},"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":"2312.05915","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-10T15:28:56Z","cross_cats_sorted":[],"title_canon_sha256":"9a70b49b31ada040ca54d14eaacca21e16f8bee1da9a7166cc73be5cbdca5a48","abstract_canon_sha256":"90771c1551da83ff5c90ff219433538a1293d03babbc21afc8877b7d9b45b4c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:06.387325Z","signature_b64":"fAW8NCLbNYEeSgbSKafme2K/iKggCUvnPtHkQmFoTBBCh44+UprcdcOqvNLuj5IjAs04vcl+Nat0Mz5irRnhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03d2d4f268fe9c1afd936c547c1c23443803bcf1973dbeac715ffd731879db4d","last_reissued_at":"2026-07-05T09:44:06.386845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:06.386845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion for Natural Image Matting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Humphrey Shi, Wei Wang, Yao Zhao, Yihan Hu, Yiheng Lin, Yunchao Wei","submitted_at":"2023-12-10T15:28:56Z","abstract_excerpt":"We aim to leverage diffusion to address the challenging image matting task. However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles to achieving this goal. In this paper, we present DiffMatte, a solution designed to effectively overcome these challenges. First, DiffMatte decouples the decoder from the intricately coupled matting network design, involving only one lightweight decoder in the iterations of the diffusion process. With such a strategy, DiffMatte mitigates the growth of compu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05915","kind":"arxiv","version":2},"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/2312.05915/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":"2312.05915","created_at":"2026-07-05T09:44:06.386892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05915v2","created_at":"2026-07-05T09:44:06.386892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05915","created_at":"2026-07-05T09:44:06.386892+00:00"},{"alias_kind":"pith_short_12","alias_value":"APJNJ4TI72OB","created_at":"2026-07-05T09:44:06.386892+00:00"},{"alias_kind":"pith_short_16","alias_value":"APJNJ4TI72OBV7MT","created_at":"2026-07-05T09:44:06.386892+00:00"},{"alias_kind":"pith_short_8","alias_value":"APJNJ4TI","created_at":"2026-07-05T09:44:06.386892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01197","citing_title":"LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APJNJ4TI72OBV7MTNRKHYHBDIQ","json":"https://pith.science/pith/APJNJ4TI72OBV7MTNRKHYHBDIQ.json","graph_json":"https://pith.science/api/pith-number/APJNJ4TI72OBV7MTNRKHYHBDIQ/graph.json","events_json":"https://pith.science/api/pith-number/APJNJ4TI72OBV7MTNRKHYHBDIQ/events.json","paper":"https://pith.science/paper/APJNJ4TI"},"agent_actions":{"view_html":"https://pith.science/pith/APJNJ4TI72OBV7MTNRKHYHBDIQ","download_json":"https://pith.science/pith/APJNJ4TI72OBV7MTNRKHYHBDIQ.json","view_paper":"https://pith.science/paper/APJNJ4TI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05915&json=true","fetch_graph":"https://pith.science/api/pith-number/APJNJ4TI72OBV7MTNRKHYHBDIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/APJNJ4TI72OBV7MTNRKHYHBDIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APJNJ4TI72OBV7MTNRKHYHBDIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APJNJ4TI72OBV7MTNRKHYHBDIQ/action/storage_attestation","attest_author":"https://pith.science/pith/APJNJ4TI72OBV7MTNRKHYHBDIQ/action/author_attestation","sign_citation":"https://pith.science/pith/APJNJ4TI72OBV7MTNRKHYHBDIQ/action/citation_signature","submit_replication":"https://pith.science/pith/APJNJ4TI72OBV7MTNRKHYHBDIQ/action/replication_record"}},"created_at":"2026-07-05T09:44:06.386892+00:00","updated_at":"2026-07-05T09:44:06.386892+00:00"}