{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OFUO5GV7B2G77NMWTJJSUK2C23","short_pith_number":"pith:OFUO5GV7","schema_version":"1.0","canonical_sha256":"7168ee9abf0e8dffb5969a532a2b42d6d661c89a2c8b08bb2ff8d055ef2141b3","source":{"kind":"arxiv","id":"2108.02938","version":2},"attestation_state":"computed","paper":{"title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jooyoung Choi, Sungroh Yoon, Sungwon Kim, Yonghyun Jeong, Youngjune Gwon","submitted_at":"2021-08-06T04:43:13Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPM) have shown remarkable performance in unconditional image generation. However, due to the stochasticity of the generative process in DDPM, it is challenging to generate images with the desired semantics. In this work, we propose Iterative Latent Variable Refinement (ILVR), a method to guide the generative process in DDPM to generate high-quality images based on a given reference image. Here, the refinement of the generative process in DDPM enables a single DDPM to sample images from various sets directed by the reference image. The proposed ILVR m"},"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":"2108.02938","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-06T04:43:13Z","cross_cats_sorted":[],"title_canon_sha256":"19cb277b473d87501d5899164e5904a56d986dafcefbba75ecf409902ecd53e3","abstract_canon_sha256":"448536a376e947b029e2f8217e9ab59eb1fe2e0dafa7a908ff0b4daab154b9ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:36.088836Z","signature_b64":"TBZy+PG7IWYUvXjrQmkJ+0j6S91fe0VoX/bm3W77G76R7upSUp9BmxWoB/oi+dkuf1AqwFwzJZOABk9dmMwSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7168ee9abf0e8dffb5969a532a2b42d6d661c89a2c8b08bb2ff8d055ef2141b3","last_reissued_at":"2026-07-05T03:14:36.088395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:36.088395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jooyoung Choi, Sungroh Yoon, Sungwon Kim, Yonghyun Jeong, Youngjune Gwon","submitted_at":"2021-08-06T04:43:13Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPM) have shown remarkable performance in unconditional image generation. However, due to the stochasticity of the generative process in DDPM, it is challenging to generate images with the desired semantics. In this work, we propose Iterative Latent Variable Refinement (ILVR), a method to guide the generative process in DDPM to generate high-quality images based on a given reference image. Here, the refinement of the generative process in DDPM enables a single DDPM to sample images from various sets directed by the reference image. The proposed ILVR m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02938","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/2108.02938/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":"2108.02938","created_at":"2026-07-05T03:14:36.088455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.02938v2","created_at":"2026-07-05T03:14:36.088455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02938","created_at":"2026-07-05T03:14:36.088455+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFUO5GV7B2G7","created_at":"2026-07-05T03:14:36.088455+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFUO5GV7B2G77NMW","created_at":"2026-07-05T03:14:36.088455+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFUO5GV7","created_at":"2026-07-05T03:14:36.088455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06813","citing_title":"Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28900","citing_title":"Spectral Guidance for Flexible and Efficient Control of Diffusion Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2411.19182","citing_title":"SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2412.08079","citing_title":"Regional climate risk assessment from climate models using probabilistic machine learning","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07715","citing_title":"Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17353","citing_title":"Dual Ascent Diffusion for Inverse Problems","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2601.05127","citing_title":"LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21045","citing_title":"LPNSR: Optimal Noise-Guided Diffusion Image Super-Resolution Via Learnable Noise Prediction","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2108.01073","citing_title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2208.01618","citing_title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05387","citing_title":"Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21315","citing_title":"TopoStyle: Supporting Iterative Design with Generative AI for 2.5D Topology Optimization","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17986","citing_title":"Latent Fourier Transform","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12575","citing_title":"StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13028","citing_title":"Conflated Inverse Modeling to Generate Diverse and Temperature-Change Inducing Urban Vegetation Patterns","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06881","citing_title":"MENO: MeanFlow-Enhanced Neural Operators for Dynamical Systems","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13581","citing_title":"SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16558","citing_title":"Cross-Modal Generation: From Commodity WiFi to High-Fidelity mmWave and RFID Sensing","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFUO5GV7B2G77NMWTJJSUK2C23","json":"https://pith.science/pith/OFUO5GV7B2G77NMWTJJSUK2C23.json","graph_json":"https://pith.science/api/pith-number/OFUO5GV7B2G77NMWTJJSUK2C23/graph.json","events_json":"https://pith.science/api/pith-number/OFUO5GV7B2G77NMWTJJSUK2C23/events.json","paper":"https://pith.science/paper/OFUO5GV7"},"agent_actions":{"view_html":"https://pith.science/pith/OFUO5GV7B2G77NMWTJJSUK2C23","download_json":"https://pith.science/pith/OFUO5GV7B2G77NMWTJJSUK2C23.json","view_paper":"https://pith.science/paper/OFUO5GV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.02938&json=true","fetch_graph":"https://pith.science/api/pith-number/OFUO5GV7B2G77NMWTJJSUK2C23/graph.json","fetch_events":"https://pith.science/api/pith-number/OFUO5GV7B2G77NMWTJJSUK2C23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFUO5GV7B2G77NMWTJJSUK2C23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFUO5GV7B2G77NMWTJJSUK2C23/action/storage_attestation","attest_author":"https://pith.science/pith/OFUO5GV7B2G77NMWTJJSUK2C23/action/author_attestation","sign_citation":"https://pith.science/pith/OFUO5GV7B2G77NMWTJJSUK2C23/action/citation_signature","submit_replication":"https://pith.science/pith/OFUO5GV7B2G77NMWTJJSUK2C23/action/replication_record"}},"created_at":"2026-07-05T03:14:36.088455+00:00","updated_at":"2026-07-05T03:14:36.088455+00:00"}