{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:434T4O5PJRHYAOTSIPCF3HZIFO","short_pith_number":"pith:434T4O5P","schema_version":"1.0","canonical_sha256":"e6f93e3baf4c4f803a7243c45d9f282ba9fc7b164e72dba203ecf3d42d935a6e","source":{"kind":"arxiv","id":"2503.17059","version":1},"attestation_state":"computed","paper":{"title":"DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.GR","authors_text":"Jifeng Ning, Mingming Gong, Shaoli Huang, Xuelin Chen, Yongkang Cheng","submitted_at":"2025-03-21T11:23:39Z","abstract_excerpt":"Diffusion models have demonstrated remarkable synthesis quality and diversity in generating co-speech gestures. However, the computationally intensive sampling steps associated with diffusion models hinder their practicality in real-world applications. Hence, we present DIDiffGes, for a Decoupled Semi-Implicit Diffusion model-based framework, that can synthesize high-quality, expressive gestures from speech using only a few sampling steps. Our approach leverages Generative Adversarial Networks (GANs) to enable large-step sampling for diffusion model. We decouple gesture data into body and hand"},"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":"2503.17059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2025-03-21T11:23:39Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"dfac5d52c0dc9b91190c522b31fd6ab5fbf682a01bd217294d89c177fbb4e5ad","abstract_canon_sha256":"ebec63ea42ce7ad490f796a84c913009791d23f151b2653a48f685606b585457"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:56.604062Z","signature_b64":"846ABDVMS3Ya+Lxe/sI+H0FhUF7/ZkmujchndDzpeiUYetlyesQJGRhrBlgiTyd8WTdAKOtoYfHxEt2+P40dDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6f93e3baf4c4f803a7243c45d9f282ba9fc7b164e72dba203ecf3d42d935a6e","last_reissued_at":"2026-07-05T10:36:56.603464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:56.603464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.GR","authors_text":"Jifeng Ning, Mingming Gong, Shaoli Huang, Xuelin Chen, Yongkang Cheng","submitted_at":"2025-03-21T11:23:39Z","abstract_excerpt":"Diffusion models have demonstrated remarkable synthesis quality and diversity in generating co-speech gestures. However, the computationally intensive sampling steps associated with diffusion models hinder their practicality in real-world applications. Hence, we present DIDiffGes, for a Decoupled Semi-Implicit Diffusion model-based framework, that can synthesize high-quality, expressive gestures from speech using only a few sampling steps. Our approach leverages Generative Adversarial Networks (GANs) to enable large-step sampling for diffusion model. We decouple gesture data into body and hand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17059","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/2503.17059/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":"2503.17059","created_at":"2026-07-05T10:36:56.603530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17059v1","created_at":"2026-07-05T10:36:56.603530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17059","created_at":"2026-07-05T10:36:56.603530+00:00"},{"alias_kind":"pith_short_12","alias_value":"434T4O5PJRHY","created_at":"2026-07-05T10:36:56.603530+00:00"},{"alias_kind":"pith_short_16","alias_value":"434T4O5PJRHYAOTS","created_at":"2026-07-05T10:36:56.603530+00:00"},{"alias_kind":"pith_short_8","alias_value":"434T4O5P","created_at":"2026-07-05T10:36:56.603530+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/434T4O5PJRHYAOTSIPCF3HZIFO","json":"https://pith.science/pith/434T4O5PJRHYAOTSIPCF3HZIFO.json","graph_json":"https://pith.science/api/pith-number/434T4O5PJRHYAOTSIPCF3HZIFO/graph.json","events_json":"https://pith.science/api/pith-number/434T4O5PJRHYAOTSIPCF3HZIFO/events.json","paper":"https://pith.science/paper/434T4O5P"},"agent_actions":{"view_html":"https://pith.science/pith/434T4O5PJRHYAOTSIPCF3HZIFO","download_json":"https://pith.science/pith/434T4O5PJRHYAOTSIPCF3HZIFO.json","view_paper":"https://pith.science/paper/434T4O5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17059&json=true","fetch_graph":"https://pith.science/api/pith-number/434T4O5PJRHYAOTSIPCF3HZIFO/graph.json","fetch_events":"https://pith.science/api/pith-number/434T4O5PJRHYAOTSIPCF3HZIFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/434T4O5PJRHYAOTSIPCF3HZIFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/434T4O5PJRHYAOTSIPCF3HZIFO/action/storage_attestation","attest_author":"https://pith.science/pith/434T4O5PJRHYAOTSIPCF3HZIFO/action/author_attestation","sign_citation":"https://pith.science/pith/434T4O5PJRHYAOTSIPCF3HZIFO/action/citation_signature","submit_replication":"https://pith.science/pith/434T4O5PJRHYAOTSIPCF3HZIFO/action/replication_record"}},"created_at":"2026-07-05T10:36:56.603530+00:00","updated_at":"2026-07-05T10:36:56.603530+00:00"}