{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JJCI54HCRKUILKO6GCWIMCJYZF","short_pith_number":"pith:JJCI54HC","schema_version":"1.0","canonical_sha256":"4a448ef0e28aa885a9de30ac860938c9494cde914b925698726cc0a45f1ac105","source":{"kind":"arxiv","id":"2501.13087","version":2},"attestation_state":"computed","paper":{"title":"Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhijit Kundu, Akshay Krishnan, Vincent Casser, Xinchen Yan","submitted_at":"2025-01-22T18:46:47Z","abstract_excerpt":"We introduce Orchid, a unified latent diffusion model that learns a joint appearance-geometry prior to generate color, depth, and surface normal images in a single diffusion process. This unified approach is more efficient and coherent than current pipelines that use separate models for appearance and geometry. Orchid is versatile - it directly generates color, depth, and normal images from text, supports joint monocular depth and normal estimation with color-conditioned finetuning, and seamlessly inpaints large 3D regions by sampling from the joint distribution. It leverages a novel Variation"},"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":"2501.13087","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-22T18:46:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8450068931fef33bb2f0340e7e353d8e84ed085e44c5dc0e36d1acd4b54621d7","abstract_canon_sha256":"d3447cee0686bf78a3095b022ef8ed3e5b95d0d676448b363ddf55a1f0f019b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:54.415843Z","signature_b64":"uic5ZOh27FEeqhnlfATP7jLX8I6Ud118x1HQ7jMNNVyAvQQdk1G1ACE5iq8bBlCIxyXJyyK8u8o1RI5eBUMaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a448ef0e28aa885a9de30ac860938c9494cde914b925698726cc0a45f1ac105","last_reissued_at":"2026-07-05T11:57:54.415276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:54.415276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhijit Kundu, Akshay Krishnan, Vincent Casser, Xinchen Yan","submitted_at":"2025-01-22T18:46:47Z","abstract_excerpt":"We introduce Orchid, a unified latent diffusion model that learns a joint appearance-geometry prior to generate color, depth, and surface normal images in a single diffusion process. This unified approach is more efficient and coherent than current pipelines that use separate models for appearance and geometry. Orchid is versatile - it directly generates color, depth, and normal images from text, supports joint monocular depth and normal estimation with color-conditioned finetuning, and seamlessly inpaints large 3D regions by sampling from the joint distribution. It leverages a novel Variation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13087","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/2501.13087/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":"2501.13087","created_at":"2026-07-05T11:57:54.415362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13087v2","created_at":"2026-07-05T11:57:54.415362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13087","created_at":"2026-07-05T11:57:54.415362+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJCI54HCRKUI","created_at":"2026-07-05T11:57:54.415362+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJCI54HCRKUILKO6","created_at":"2026-07-05T11:57:54.415362+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJCI54HC","created_at":"2026-07-05T11:57:54.415362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13676","citing_title":"Modality Forcing for Scalable Spatial Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30370","citing_title":"MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23178","citing_title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10584","citing_title":"Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJCI54HCRKUILKO6GCWIMCJYZF","json":"https://pith.science/pith/JJCI54HCRKUILKO6GCWIMCJYZF.json","graph_json":"https://pith.science/api/pith-number/JJCI54HCRKUILKO6GCWIMCJYZF/graph.json","events_json":"https://pith.science/api/pith-number/JJCI54HCRKUILKO6GCWIMCJYZF/events.json","paper":"https://pith.science/paper/JJCI54HC"},"agent_actions":{"view_html":"https://pith.science/pith/JJCI54HCRKUILKO6GCWIMCJYZF","download_json":"https://pith.science/pith/JJCI54HCRKUILKO6GCWIMCJYZF.json","view_paper":"https://pith.science/paper/JJCI54HC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13087&json=true","fetch_graph":"https://pith.science/api/pith-number/JJCI54HCRKUILKO6GCWIMCJYZF/graph.json","fetch_events":"https://pith.science/api/pith-number/JJCI54HCRKUILKO6GCWIMCJYZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJCI54HCRKUILKO6GCWIMCJYZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJCI54HCRKUILKO6GCWIMCJYZF/action/storage_attestation","attest_author":"https://pith.science/pith/JJCI54HCRKUILKO6GCWIMCJYZF/action/author_attestation","sign_citation":"https://pith.science/pith/JJCI54HCRKUILKO6GCWIMCJYZF/action/citation_signature","submit_replication":"https://pith.science/pith/JJCI54HCRKUILKO6GCWIMCJYZF/action/replication_record"}},"created_at":"2026-07-05T11:57:54.415362+00:00","updated_at":"2026-07-05T11:57:54.415362+00:00"}