{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HYUVHGAL5P34CGZTLPY5WBSA54","short_pith_number":"pith:HYUVHGAL","schema_version":"1.0","canonical_sha256":"3e2953980bebf7c11b335bf1db0640ef150016d11dfeb2a66669eae35823eb20","source":{"kind":"arxiv","id":"2405.11794","version":2},"attestation_state":"computed","paper":{"title":"ViViD: Video Virtual Try-on using Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aimin Su, Hongliang Song, Kai Zhu, Mao Wang, Wei Zhai, Yang Cao, Yu Chen, Zheng-Jun Zha, Zhiheng Liu, Zixun Fang","submitted_at":"2024-05-20T05:28:22Z","abstract_excerpt":"Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while previous video-based try-on solutions can only generate low visual quality and blurring results. In this work, we present ViViD, a novel framework employing powerful diffusion models to tackle the task of video virtual try-on. Specifically, we design the Garment Encoder to extract fine-grained clothing semantic features, guiding the model to capture garment detail"},"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":"2405.11794","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T05:28:22Z","cross_cats_sorted":[],"title_canon_sha256":"37871c87bda432a73a11f922bc968b1331185592ad7cc3807e9660ca2ad66791","abstract_canon_sha256":"9456af2410ee972611c772f26a0a31cdeab3301ff8c8dc60acb1f627ce18efa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:05.704483Z","signature_b64":"6pFEsd34be06PonE2nUvLIZF0UpXeDD8QtMbmg2szTQKN3ZvJFPXTGyimRJdiICt4gJHgxM6ofv4JQQhYBPvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e2953980bebf7c11b335bf1db0640ef150016d11dfeb2a66669eae35823eb20","last_reissued_at":"2026-07-05T08:24:05.703982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:05.703982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViViD: Video Virtual Try-on using Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aimin Su, Hongliang Song, Kai Zhu, Mao Wang, Wei Zhai, Yang Cao, Yu Chen, Zheng-Jun Zha, Zhiheng Liu, Zixun Fang","submitted_at":"2024-05-20T05:28:22Z","abstract_excerpt":"Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while previous video-based try-on solutions can only generate low visual quality and blurring results. In this work, we present ViViD, a novel framework employing powerful diffusion models to tackle the task of video virtual try-on. Specifically, we design the Garment Encoder to extract fine-grained clothing semantic features, guiding the model to capture garment detail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11794","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/2405.11794/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":"2405.11794","created_at":"2026-07-05T08:24:05.704045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11794v2","created_at":"2026-07-05T08:24:05.704045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11794","created_at":"2026-07-05T08:24:05.704045+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYUVHGAL5P34","created_at":"2026-07-05T08:24:05.704045+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYUVHGAL5P34CGZT","created_at":"2026-07-05T08:24:05.704045+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYUVHGAL","created_at":"2026-07-05T08:24:05.704045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26092","citing_title":"TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08514","citing_title":"OmniTryOn: Video Try-On Anything at Once!","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17283","citing_title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04434","citing_title":"Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00956","citing_title":"RefTon: Reference person shot assist virtual Try-on","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18957","citing_title":"Eevee: Towards Close-up High-resolution Video-based Virtual Try-on","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20340","citing_title":"The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":246,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04934","citing_title":"Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27958","citing_title":"TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYUVHGAL5P34CGZTLPY5WBSA54","json":"https://pith.science/pith/HYUVHGAL5P34CGZTLPY5WBSA54.json","graph_json":"https://pith.science/api/pith-number/HYUVHGAL5P34CGZTLPY5WBSA54/graph.json","events_json":"https://pith.science/api/pith-number/HYUVHGAL5P34CGZTLPY5WBSA54/events.json","paper":"https://pith.science/paper/HYUVHGAL"},"agent_actions":{"view_html":"https://pith.science/pith/HYUVHGAL5P34CGZTLPY5WBSA54","download_json":"https://pith.science/pith/HYUVHGAL5P34CGZTLPY5WBSA54.json","view_paper":"https://pith.science/paper/HYUVHGAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11794&json=true","fetch_graph":"https://pith.science/api/pith-number/HYUVHGAL5P34CGZTLPY5WBSA54/graph.json","fetch_events":"https://pith.science/api/pith-number/HYUVHGAL5P34CGZTLPY5WBSA54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYUVHGAL5P34CGZTLPY5WBSA54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYUVHGAL5P34CGZTLPY5WBSA54/action/storage_attestation","attest_author":"https://pith.science/pith/HYUVHGAL5P34CGZTLPY5WBSA54/action/author_attestation","sign_citation":"https://pith.science/pith/HYUVHGAL5P34CGZTLPY5WBSA54/action/citation_signature","submit_replication":"https://pith.science/pith/HYUVHGAL5P34CGZTLPY5WBSA54/action/replication_record"}},"created_at":"2026-07-05T08:24:05.704045+00:00","updated_at":"2026-07-05T08:24:05.704045+00:00"}