{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MOXKA3VOMEVC6EKUTWKBVOUTRM","short_pith_number":"pith:MOXKA3VO","schema_version":"1.0","canonical_sha256":"63aea06eae612a2f11549d941aba938b3c0e7677ba006daa05f65baec9eddaf8","source":{"kind":"arxiv","id":"2403.12036","version":1},"attestation_state":"computed","paper":{"title":"One-Step Image Translation with Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gaurav Parmar, Jun-Yan Zhu, Srinivasa Narasimhan, Taesung Park","submitted_at":"2024-03-18T17:59:40Z","abstract_excerpt":"In this work, we address two limitations of existing conditional diffusion models: their slow inference speed due to the iterative denoising process and their reliance on paired data for model fine-tuning. To tackle these issues, we introduce a general method for adapting a single-step diffusion model to new tasks and domains through adversarial learning objectives. Specifically, we consolidate various modules of the vanilla latent diffusion model into a single end-to-end generator network with small trainable weights, enhancing its ability to preserve the input image structure while reducing "},"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":"2403.12036","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:59:40Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"5eb46a40a9f6363a5c2a56db6c727bad240aa9e8681c28cf30316720bdb7a241","abstract_canon_sha256":"b98b14339a0bc088c1e2669e0e7b21f2f737df0a4d94e4bd1a10f34524b9303e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:35.480950Z","signature_b64":"tlTnYSOqN7/u2rVnyyTGw9SiOjagiKtRz5ThqAriwPmJ5Zgs3kGTl51cuno7wtQnYwtKSJgAkhtUviUf2sh3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63aea06eae612a2f11549d941aba938b3c0e7677ba006daa05f65baec9eddaf8","last_reissued_at":"2026-07-05T07:57:35.480075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:35.480075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Step Image Translation with Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gaurav Parmar, Jun-Yan Zhu, Srinivasa Narasimhan, Taesung Park","submitted_at":"2024-03-18T17:59:40Z","abstract_excerpt":"In this work, we address two limitations of existing conditional diffusion models: their slow inference speed due to the iterative denoising process and their reliance on paired data for model fine-tuning. To tackle these issues, we introduce a general method for adapting a single-step diffusion model to new tasks and domains through adversarial learning objectives. Specifically, we consolidate various modules of the vanilla latent diffusion model into a single end-to-end generator network with small trainable weights, enhancing its ability to preserve the input image structure while reducing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12036","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/2403.12036/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":"2403.12036","created_at":"2026-07-05T07:57:35.480373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12036v1","created_at":"2026-07-05T07:57:35.480373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12036","created_at":"2026-07-05T07:57:35.480373+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOXKA3VOMEVC","created_at":"2026-07-05T07:57:35.480373+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOXKA3VOMEVC6EKU","created_at":"2026-07-05T07:57:35.480373+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOXKA3VO","created_at":"2026-07-05T07:57:35.480373+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19961","citing_title":"Addressing Detail Bottlenecks in Latent Diffusion for RGB-to-SWIR Image Translation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03246","citing_title":"MariData: One-Step Unpaired Image Translation for Maritime Environments","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31018","citing_title":"WarpI2I: Image Warping for Image-to-Image Translation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29020","citing_title":"Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27678","citing_title":"Two-Stage Cross-Domain Cervical Abnormality Screening with Cytopathological Image Synthesis and Knowledge Distillation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16406","citing_title":"Contrastive-SDXL: Annotation-Preserving Night-Time Augmentation for Pedestrian Detection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07826","citing_title":"R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2508.21435","citing_title":"MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2601.05127","citing_title":"LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17812","citing_title":"ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13815","citing_title":"OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02003","citing_title":"ProDiG: Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12399","citing_title":"GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21518","citing_title":"DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00177","citing_title":"FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19257","citing_title":"Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09511","citing_title":"RIRF: Reasoning Image Restoration Framework","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05687","citing_title":"3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13416","citing_title":"DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOXKA3VOMEVC6EKUTWKBVOUTRM","json":"https://pith.science/pith/MOXKA3VOMEVC6EKUTWKBVOUTRM.json","graph_json":"https://pith.science/api/pith-number/MOXKA3VOMEVC6EKUTWKBVOUTRM/graph.json","events_json":"https://pith.science/api/pith-number/MOXKA3VOMEVC6EKUTWKBVOUTRM/events.json","paper":"https://pith.science/paper/MOXKA3VO"},"agent_actions":{"view_html":"https://pith.science/pith/MOXKA3VOMEVC6EKUTWKBVOUTRM","download_json":"https://pith.science/pith/MOXKA3VOMEVC6EKUTWKBVOUTRM.json","view_paper":"https://pith.science/paper/MOXKA3VO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12036&json=true","fetch_graph":"https://pith.science/api/pith-number/MOXKA3VOMEVC6EKUTWKBVOUTRM/graph.json","fetch_events":"https://pith.science/api/pith-number/MOXKA3VOMEVC6EKUTWKBVOUTRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOXKA3VOMEVC6EKUTWKBVOUTRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOXKA3VOMEVC6EKUTWKBVOUTRM/action/storage_attestation","attest_author":"https://pith.science/pith/MOXKA3VOMEVC6EKUTWKBVOUTRM/action/author_attestation","sign_citation":"https://pith.science/pith/MOXKA3VOMEVC6EKUTWKBVOUTRM/action/citation_signature","submit_replication":"https://pith.science/pith/MOXKA3VOMEVC6EKUTWKBVOUTRM/action/replication_record"}},"created_at":"2026-07-05T07:57:35.480373+00:00","updated_at":"2026-07-05T07:57:35.480373+00:00"}