{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S433ZWLMBIRRBSMSPMVS4CWR5I","short_pith_number":"pith:S433ZWLM","schema_version":"1.0","canonical_sha256":"9737bcd96c0a2310c9927b2b2e0ad1ea2dab8935b1a7d02a494911a3084111b7","source":{"kind":"arxiv","id":"2402.01516","version":2},"attestation_state":"computed","paper":{"title":"Cross-view Masked Diffusion Transformers for Person Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang D. Yoo, Trung X. Pham, Zhang Kang","submitted_at":"2024-02-02T15:57:13Z","abstract_excerpt":"We present X-MDPT ($\\underline{Cross}$-view $\\underline{M}$asked $\\underline{D}$iffusion $\\underline{P}$rediction $\\underline{T}$ransformers), a novel diffusion model designed for pose-guided human image generation. X-MDPT distinguishes itself by employing masked diffusion transformers that operate on latent patches, a departure from the commonly-used Unet structures in existing works. The model comprises three key modules: 1) a denoising diffusion Transformer, 2) an aggregation network that consolidates conditions into a single vector for the diffusion process, and 3) a mask cross-prediction "},"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":"2402.01516","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-02T15:57:13Z","cross_cats_sorted":[],"title_canon_sha256":"996527522bbc460d54f55d6eb2e7376b48991a6ba80f3e16163d152a1ac98053","abstract_canon_sha256":"1ba9ee25019d003a38c9e31ed9de6a3163d43895d988519cdfacede8638c8dd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:18.578003Z","signature_b64":"de8SwaQuBeJiZTAi6LT/bAKlTVz3v5vH/A/Pfu1int7EOfrVf6Zpbahnv/ePGGbRLmOIvnaulA5dobzbYHWaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9737bcd96c0a2310c9927b2b2e0ad1ea2dab8935b1a7d02a494911a3084111b7","last_reissued_at":"2026-07-05T08:26:18.577514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:18.577514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-view Masked Diffusion Transformers for Person Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang D. Yoo, Trung X. Pham, Zhang Kang","submitted_at":"2024-02-02T15:57:13Z","abstract_excerpt":"We present X-MDPT ($\\underline{Cross}$-view $\\underline{M}$asked $\\underline{D}$iffusion $\\underline{P}$rediction $\\underline{T}$ransformers), a novel diffusion model designed for pose-guided human image generation. X-MDPT distinguishes itself by employing masked diffusion transformers that operate on latent patches, a departure from the commonly-used Unet structures in existing works. The model comprises three key modules: 1) a denoising diffusion Transformer, 2) an aggregation network that consolidates conditions into a single vector for the diffusion process, and 3) a mask cross-prediction "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01516","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/2402.01516/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":"2402.01516","created_at":"2026-07-05T08:26:18.577575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01516v2","created_at":"2026-07-05T08:26:18.577575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01516","created_at":"2026-07-05T08:26:18.577575+00:00"},{"alias_kind":"pith_short_12","alias_value":"S433ZWLMBIRR","created_at":"2026-07-05T08:26:18.577575+00:00"},{"alias_kind":"pith_short_16","alias_value":"S433ZWLMBIRRBSMS","created_at":"2026-07-05T08:26:18.577575+00:00"},{"alias_kind":"pith_short_8","alias_value":"S433ZWLM","created_at":"2026-07-05T08:26:18.577575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S433ZWLMBIRRBSMSPMVS4CWR5I","json":"https://pith.science/pith/S433ZWLMBIRRBSMSPMVS4CWR5I.json","graph_json":"https://pith.science/api/pith-number/S433ZWLMBIRRBSMSPMVS4CWR5I/graph.json","events_json":"https://pith.science/api/pith-number/S433ZWLMBIRRBSMSPMVS4CWR5I/events.json","paper":"https://pith.science/paper/S433ZWLM"},"agent_actions":{"view_html":"https://pith.science/pith/S433ZWLMBIRRBSMSPMVS4CWR5I","download_json":"https://pith.science/pith/S433ZWLMBIRRBSMSPMVS4CWR5I.json","view_paper":"https://pith.science/paper/S433ZWLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01516&json=true","fetch_graph":"https://pith.science/api/pith-number/S433ZWLMBIRRBSMSPMVS4CWR5I/graph.json","fetch_events":"https://pith.science/api/pith-number/S433ZWLMBIRRBSMSPMVS4CWR5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S433ZWLMBIRRBSMSPMVS4CWR5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S433ZWLMBIRRBSMSPMVS4CWR5I/action/storage_attestation","attest_author":"https://pith.science/pith/S433ZWLMBIRRBSMSPMVS4CWR5I/action/author_attestation","sign_citation":"https://pith.science/pith/S433ZWLMBIRRBSMSPMVS4CWR5I/action/citation_signature","submit_replication":"https://pith.science/pith/S433ZWLMBIRRBSMSPMVS4CWR5I/action/replication_record"}},"created_at":"2026-07-05T08:26:18.577575+00:00","updated_at":"2026-07-05T08:26:18.577575+00:00"}