{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2JJ3KQPLYQ7PFE4CT5ED2YI63E","short_pith_number":"pith:2JJ3KQPL","schema_version":"1.0","canonical_sha256":"d253b541ebc43ef293829f483d611ed9379891e210a7fb4370656922cb06f1e1","source":{"kind":"arxiv","id":"2312.03079","version":1},"attestation_state":"computed","paper":{"title":"LooseControl: Lifting ControlNet for Generalized Depth Conditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Niloy J. Mitra, Peter Wonka, Shariq Farooq Bhat","submitted_at":"2023-12-05T19:00:20Z","abstract_excerpt":"We present LooseControl to allow generalized depth conditioning for diffusion-based image generation. ControlNet, the SOTA for depth-conditioned image generation, produces remarkable results but relies on having access to detailed depth maps for guidance. Creating such exact depth maps, in many scenarios, is challenging. This paper introduces a generalized version of depth conditioning that enables many new content-creation workflows. Specifically, we allow (C1) scene boundary control for loosely specifying scenes with only boundary conditions, and (C2) 3D box control for specifying layout loc"},"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":"2312.03079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T19:00:20Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"476ce63aa5d2decb7e54e2d76bcf1262eb05ed61b992c187922ca17412062cb9","abstract_canon_sha256":"cda86e883d4c932eb21544a84558d1b2854c117a8f25c6a1cdc03622aa0922ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:57.814746Z","signature_b64":"4Zv+fpzzb30P01T+BwlBGVPU6c8bLhdYMoqqvDCQozc8B73OzAL4J9FKFGeVj2CiUiBFxe38djJLRNj7HskECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d253b541ebc43ef293829f483d611ed9379891e210a7fb4370656922cb06f1e1","last_reissued_at":"2026-07-05T07:20:57.814259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:57.814259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LooseControl: Lifting ControlNet for Generalized Depth Conditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Niloy J. Mitra, Peter Wonka, Shariq Farooq Bhat","submitted_at":"2023-12-05T19:00:20Z","abstract_excerpt":"We present LooseControl to allow generalized depth conditioning for diffusion-based image generation. ControlNet, the SOTA for depth-conditioned image generation, produces remarkable results but relies on having access to detailed depth maps for guidance. Creating such exact depth maps, in many scenarios, is challenging. This paper introduces a generalized version of depth conditioning that enables many new content-creation workflows. Specifically, we allow (C1) scene boundary control for loosely specifying scenes with only boundary conditions, and (C2) 3D box control for specifying layout loc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03079","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/2312.03079/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":"2312.03079","created_at":"2026-07-05T07:20:57.814325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03079v1","created_at":"2026-07-05T07:20:57.814325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03079","created_at":"2026-07-05T07:20:57.814325+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JJ3KQPLYQ7P","created_at":"2026-07-05T07:20:57.814325+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JJ3KQPLYQ7PFE4C","created_at":"2026-07-05T07:20:57.814325+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JJ3KQPL","created_at":"2026-07-05T07:20:57.814325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31924","citing_title":"InstanceControl: Controllable Complex Image Generation without Instance Labeling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19741","citing_title":"CityRAG: Stepping Into a City via Spatially-Grounded Video Generation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JJ3KQPLYQ7PFE4CT5ED2YI63E","json":"https://pith.science/pith/2JJ3KQPLYQ7PFE4CT5ED2YI63E.json","graph_json":"https://pith.science/api/pith-number/2JJ3KQPLYQ7PFE4CT5ED2YI63E/graph.json","events_json":"https://pith.science/api/pith-number/2JJ3KQPLYQ7PFE4CT5ED2YI63E/events.json","paper":"https://pith.science/paper/2JJ3KQPL"},"agent_actions":{"view_html":"https://pith.science/pith/2JJ3KQPLYQ7PFE4CT5ED2YI63E","download_json":"https://pith.science/pith/2JJ3KQPLYQ7PFE4CT5ED2YI63E.json","view_paper":"https://pith.science/paper/2JJ3KQPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03079&json=true","fetch_graph":"https://pith.science/api/pith-number/2JJ3KQPLYQ7PFE4CT5ED2YI63E/graph.json","fetch_events":"https://pith.science/api/pith-number/2JJ3KQPLYQ7PFE4CT5ED2YI63E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JJ3KQPLYQ7PFE4CT5ED2YI63E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JJ3KQPLYQ7PFE4CT5ED2YI63E/action/storage_attestation","attest_author":"https://pith.science/pith/2JJ3KQPLYQ7PFE4CT5ED2YI63E/action/author_attestation","sign_citation":"https://pith.science/pith/2JJ3KQPLYQ7PFE4CT5ED2YI63E/action/citation_signature","submit_replication":"https://pith.science/pith/2JJ3KQPLYQ7PFE4CT5ED2YI63E/action/replication_record"}},"created_at":"2026-07-05T07:20:57.814325+00:00","updated_at":"2026-07-05T07:20:57.814325+00:00"}