{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6GR57LBYDC75U5JCDBIGGOOBA5","short_pith_number":"pith:6GR57LBY","schema_version":"1.0","canonical_sha256":"f1a3dfac3818bfda752218506339c10760e0373de1f00b36a567cb99c3f0877d","source":{"kind":"arxiv","id":"2405.00954","version":1},"attestation_state":"computed","paper":{"title":"X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi Ji, Rongrong Ji, Xiaoshuai Sun, Yijun Fan, Yiwei Ma, Zhekai Lin","submitted_at":"2024-05-02T02:30:39Z","abstract_excerpt":"Recent advancements in automatic 3D avatar generation guided by text have made significant progress. However, existing methods have limitations such as oversaturation and low-quality output. To address these challenges, we propose X-Oscar, a progressive framework for generating high-quality animatable avatars from text prompts. It follows a sequential Geometry->Texture->Animation paradigm, simplifying optimization through step-by-step generation. To tackle oversaturation, we introduce Adaptive Variational Parameter (AVP), representing avatars as an adaptive distribution during training. Additi"},"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":"2405.00954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T02:30:39Z","cross_cats_sorted":[],"title_canon_sha256":"2f4f168099df4342e5d1711a0c2b2be01d99d1f0c5c2bcefc912d657d4ffe2d9","abstract_canon_sha256":"b9a01eb37f0b7b5a8ffaa364d92562b52a5c13a872fce05cd36cf2498967900f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:28.462791Z","signature_b64":"ZQHJom2KYgGXZumj8BR4IR/pu2U98qUKDrhywtHMuDA9BwqONDIBnBkdQInOO/R2grQfp1kdkrOundt4pUPeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1a3dfac3818bfda752218506339c10760e0373de1f00b36a567cb99c3f0877d","last_reissued_at":"2026-07-05T08:14:28.462327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:28.462327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi Ji, Rongrong Ji, Xiaoshuai Sun, Yijun Fan, Yiwei Ma, Zhekai Lin","submitted_at":"2024-05-02T02:30:39Z","abstract_excerpt":"Recent advancements in automatic 3D avatar generation guided by text have made significant progress. However, existing methods have limitations such as oversaturation and low-quality output. To address these challenges, we propose X-Oscar, a progressive framework for generating high-quality animatable avatars from text prompts. It follows a sequential Geometry->Texture->Animation paradigm, simplifying optimization through step-by-step generation. To tackle oversaturation, we introduce Adaptive Variational Parameter (AVP), representing avatars as an adaptive distribution during training. Additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00954","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/2405.00954/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":"2405.00954","created_at":"2026-07-05T08:14:28.462385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00954v1","created_at":"2026-07-05T08:14:28.462385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00954","created_at":"2026-07-05T08:14:28.462385+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GR57LBYDC75","created_at":"2026-07-05T08:14:28.462385+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GR57LBYDC75U5JC","created_at":"2026-07-05T08:14:28.462385+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GR57LBY","created_at":"2026-07-05T08:14:28.462385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08977","citing_title":"Text-driven 3D Human Generation via Contrastive Preference Optimization","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GR57LBYDC75U5JCDBIGGOOBA5","json":"https://pith.science/pith/6GR57LBYDC75U5JCDBIGGOOBA5.json","graph_json":"https://pith.science/api/pith-number/6GR57LBYDC75U5JCDBIGGOOBA5/graph.json","events_json":"https://pith.science/api/pith-number/6GR57LBYDC75U5JCDBIGGOOBA5/events.json","paper":"https://pith.science/paper/6GR57LBY"},"agent_actions":{"view_html":"https://pith.science/pith/6GR57LBYDC75U5JCDBIGGOOBA5","download_json":"https://pith.science/pith/6GR57LBYDC75U5JCDBIGGOOBA5.json","view_paper":"https://pith.science/paper/6GR57LBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00954&json=true","fetch_graph":"https://pith.science/api/pith-number/6GR57LBYDC75U5JCDBIGGOOBA5/graph.json","fetch_events":"https://pith.science/api/pith-number/6GR57LBYDC75U5JCDBIGGOOBA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GR57LBYDC75U5JCDBIGGOOBA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GR57LBYDC75U5JCDBIGGOOBA5/action/storage_attestation","attest_author":"https://pith.science/pith/6GR57LBYDC75U5JCDBIGGOOBA5/action/author_attestation","sign_citation":"https://pith.science/pith/6GR57LBYDC75U5JCDBIGGOOBA5/action/citation_signature","submit_replication":"https://pith.science/pith/6GR57LBYDC75U5JCDBIGGOOBA5/action/replication_record"}},"created_at":"2026-07-05T08:14:28.462385+00:00","updated_at":"2026-07-05T08:14:28.462385+00:00"}