{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UGEQSNY2MJ2YAECZCGROL7FBYM","short_pith_number":"pith:UGEQSNY2","schema_version":"1.0","canonical_sha256":"a18909371a627580105911a2e5fca1c31c45498e38e3ee04eac53e5a750b31a8","source":{"kind":"arxiv","id":"2307.09781","version":1},"attestation_state":"computed","paper":{"title":"Text2Layer: Layered Image Generation using Latent Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jeff Chien, Wentian Zhao, Xin Lu, Xinyang Zhang","submitted_at":"2023-07-19T06:56:07Z","abstract_excerpt":"Layer compositing is one of the most popular image editing workflows among both amateurs and professionals. Motivated by the success of diffusion models, we explore layer compositing from a layered image generation perspective. Instead of generating an image, we propose to generate background, foreground, layer mask, and the composed image simultaneously. To achieve layered image generation, we train an autoencoder that is able to reconstruct layered images and train diffusion models on the latent representation. One benefit of the proposed problem is to enable better compositing workflows in "},"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":"2307.09781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T06:56:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ddd29b1a3179376774052cdfd081697eb9089fb8f7e33cc592de9c72b3422847","abstract_canon_sha256":"6b5b9ac82fd99b37522071bd6e179da287921ad6b7a22b5f636cde73e7b53f0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:46.275263Z","signature_b64":"cF8UpSn+foFIeEDyotneP3Wg/fgdDpKclb734g72oiMpZW36/Vz9GKTnLAJBZCSEKkJJ4ZObIX8gitHPgHPuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a18909371a627580105911a2e5fca1c31c45498e38e3ee04eac53e5a750b31a8","last_reissued_at":"2026-07-05T06:32:46.274837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:46.274837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text2Layer: Layered Image Generation using Latent Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jeff Chien, Wentian Zhao, Xin Lu, Xinyang Zhang","submitted_at":"2023-07-19T06:56:07Z","abstract_excerpt":"Layer compositing is one of the most popular image editing workflows among both amateurs and professionals. Motivated by the success of diffusion models, we explore layer compositing from a layered image generation perspective. Instead of generating an image, we propose to generate background, foreground, layer mask, and the composed image simultaneously. To achieve layered image generation, we train an autoencoder that is able to reconstruct layered images and train diffusion models on the latent representation. One benefit of the proposed problem is to enable better compositing workflows in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09781","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/2307.09781/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":"2307.09781","created_at":"2026-07-05T06:32:46.274897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.09781v1","created_at":"2026-07-05T06:32:46.274897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09781","created_at":"2026-07-05T06:32:46.274897+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGEQSNY2MJ2Y","created_at":"2026-07-05T06:32:46.274897+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGEQSNY2MJ2YAECZ","created_at":"2026-07-05T06:32:46.274897+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGEQSNY2","created_at":"2026-07-05T06:32:46.274897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14552","citing_title":"LiWi: Layering in the Wild","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27235","citing_title":"MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14552","citing_title":"LiWi: Layering in the Wild","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15507","citing_title":"A Unified and Controllable Framework for Layered Image Generation with Visual Effects","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14552","citing_title":"LiWi: Layering in the Wild","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11818","citing_title":"RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10319","citing_title":"LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGEQSNY2MJ2YAECZCGROL7FBYM","json":"https://pith.science/pith/UGEQSNY2MJ2YAECZCGROL7FBYM.json","graph_json":"https://pith.science/api/pith-number/UGEQSNY2MJ2YAECZCGROL7FBYM/graph.json","events_json":"https://pith.science/api/pith-number/UGEQSNY2MJ2YAECZCGROL7FBYM/events.json","paper":"https://pith.science/paper/UGEQSNY2"},"agent_actions":{"view_html":"https://pith.science/pith/UGEQSNY2MJ2YAECZCGROL7FBYM","download_json":"https://pith.science/pith/UGEQSNY2MJ2YAECZCGROL7FBYM.json","view_paper":"https://pith.science/paper/UGEQSNY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.09781&json=true","fetch_graph":"https://pith.science/api/pith-number/UGEQSNY2MJ2YAECZCGROL7FBYM/graph.json","fetch_events":"https://pith.science/api/pith-number/UGEQSNY2MJ2YAECZCGROL7FBYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGEQSNY2MJ2YAECZCGROL7FBYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGEQSNY2MJ2YAECZCGROL7FBYM/action/storage_attestation","attest_author":"https://pith.science/pith/UGEQSNY2MJ2YAECZCGROL7FBYM/action/author_attestation","sign_citation":"https://pith.science/pith/UGEQSNY2MJ2YAECZCGROL7FBYM/action/citation_signature","submit_replication":"https://pith.science/pith/UGEQSNY2MJ2YAECZCGROL7FBYM/action/replication_record"}},"created_at":"2026-07-05T06:32:46.274897+00:00","updated_at":"2026-07-05T06:32:46.274897+00:00"}