{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PJZCRH5I7KF3C62ML7KHRYMYSK","short_pith_number":"pith:PJZCRH5I","schema_version":"1.0","canonical_sha256":"7a72289fa8fa8bb17b4c5fd478e1989299c3fb67558e38adf2629d09ecbd8b33","source":{"kind":"arxiv","id":"2411.17864","version":1},"attestation_state":"computed","paper":{"title":"Generative Image Layer Decomposition with Visual Effects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Daniil Pakhomov, Jianming Zhang, Jinrui Yang, Mengwei Ren, Qing Liu, Soo Ye Kim, Yijun Li, Yuyin Zhou, Zhe Lin","submitted_at":"2024-11-26T20:26:49Z","abstract_excerpt":"Recent advancements in large generative models, particularly diffusion-based methods, have significantly enhanced the capabilities of image editing. However, achieving precise control over image composition tasks remains a challenge. Layered representations, which allow for independent editing of image components, are essential for user-driven content creation, yet existing approaches often struggle to decompose image into plausible layers with accurately retained transparent visual effects such as shadows and reflections. We propose $\\textbf{LayerDecomp}$, a generative framework for image lay"},"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":"2411.17864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T20:26:49Z","cross_cats_sorted":[],"title_canon_sha256":"4b7a66ffcc82800c502fe0fed5351cc6d5e2a7515eacec3c991455154e6ecbc2","abstract_canon_sha256":"0b101c056e78b3e4d6b7dcbc9fda55dd61d9f1789a0f120bb7a35d1f71b015ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:08.161091Z","signature_b64":"Xke80I7hLUUSvFmE1TbJGzLzM4qWn1y3VzwZSEGDaUwBORa+ODRFU+Cowo64drIFQMPNfB1x7j6ygjSmZaQfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a72289fa8fa8bb17b4c5fd478e1989299c3fb67558e38adf2629d09ecbd8b33","last_reissued_at":"2026-07-05T09:41:08.160681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:08.160681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Image Layer Decomposition with Visual Effects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Daniil Pakhomov, Jianming Zhang, Jinrui Yang, Mengwei Ren, Qing Liu, Soo Ye Kim, Yijun Li, Yuyin Zhou, Zhe Lin","submitted_at":"2024-11-26T20:26:49Z","abstract_excerpt":"Recent advancements in large generative models, particularly diffusion-based methods, have significantly enhanced the capabilities of image editing. However, achieving precise control over image composition tasks remains a challenge. Layered representations, which allow for independent editing of image components, are essential for user-driven content creation, yet existing approaches often struggle to decompose image into plausible layers with accurately retained transparent visual effects such as shadows and reflections. We propose $\\textbf{LayerDecomp}$, a generative framework for image lay"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17864","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/2411.17864/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":"2411.17864","created_at":"2026-07-05T09:41:08.160734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17864v1","created_at":"2026-07-05T09:41:08.160734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17864","created_at":"2026-07-05T09:41:08.160734+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJZCRH5I7KF3","created_at":"2026-07-05T09:41:08.160734+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJZCRH5I7KF3C62M","created_at":"2026-07-05T09:41:08.160734+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJZCRH5I","created_at":"2026-07-05T09:41:08.160734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09308","citing_title":"AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJZCRH5I7KF3C62ML7KHRYMYSK","json":"https://pith.science/pith/PJZCRH5I7KF3C62ML7KHRYMYSK.json","graph_json":"https://pith.science/api/pith-number/PJZCRH5I7KF3C62ML7KHRYMYSK/graph.json","events_json":"https://pith.science/api/pith-number/PJZCRH5I7KF3C62ML7KHRYMYSK/events.json","paper":"https://pith.science/paper/PJZCRH5I"},"agent_actions":{"view_html":"https://pith.science/pith/PJZCRH5I7KF3C62ML7KHRYMYSK","download_json":"https://pith.science/pith/PJZCRH5I7KF3C62ML7KHRYMYSK.json","view_paper":"https://pith.science/paper/PJZCRH5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17864&json=true","fetch_graph":"https://pith.science/api/pith-number/PJZCRH5I7KF3C62ML7KHRYMYSK/graph.json","fetch_events":"https://pith.science/api/pith-number/PJZCRH5I7KF3C62ML7KHRYMYSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJZCRH5I7KF3C62ML7KHRYMYSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJZCRH5I7KF3C62ML7KHRYMYSK/action/storage_attestation","attest_author":"https://pith.science/pith/PJZCRH5I7KF3C62ML7KHRYMYSK/action/author_attestation","sign_citation":"https://pith.science/pith/PJZCRH5I7KF3C62ML7KHRYMYSK/action/citation_signature","submit_replication":"https://pith.science/pith/PJZCRH5I7KF3C62ML7KHRYMYSK/action/replication_record"}},"created_at":"2026-07-05T09:41:08.160734+00:00","updated_at":"2026-07-05T09:41:08.160734+00:00"}