{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J5JEE6ZC6YQY3RJKMWLI7RF62D","short_pith_number":"pith:J5JEE6ZC","schema_version":"1.0","canonical_sha256":"4f52427b22f6218dc52a65968fc4bed0d5499fa06ade0935f910d692de227118","source":{"kind":"arxiv","id":"2407.06938","version":2},"attestation_state":"computed","paper":{"title":"RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Bowen Zhang, Chunyu Wang, Dong Chen, Feng Zhao, Jiaolong Yang, Ting Zhang, Yansong Tang, Yiji Cheng","submitted_at":"2024-07-09T15:14:45Z","abstract_excerpt":"We present RodinHD, which can generate high-fidelity 3D avatars from a portrait image. Existing methods fail to capture intricate details such as hairstyles which we tackle in this paper. We first identify an overlooked problem of catastrophic forgetting that arises when fitting triplanes sequentially on many avatars, caused by the MLP decoder sharing scheme. To overcome this issue, we raise a novel data scheduling strategy and a weight consolidation regularization term, which improves the decoder's capability of rendering sharper details. Additionally, we optimize the guiding effect of the po"},"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":"2407.06938","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T15:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"cbeaca57c6c26c49e7f4f88a24d4d6907de7a1c29e83de9396993bde34378d34","abstract_canon_sha256":"93dc2d5b46b1b1b8e21b936b0bc10d1c96492ad1ec71e3cc3e175ed6000aa9f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:39.087289Z","signature_b64":"8/kbc+O2Xjp7AdNDz0aUIxiFZmjDFNzw9/5V+vF0+sJpLmssIGMRp6uErmfI/w2no6bbk1qMHpECX+esc9GUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f52427b22f6218dc52a65968fc4bed0d5499fa06ade0935f910d692de227118","last_reissued_at":"2026-07-05T08:42:39.086824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:39.086824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Bowen Zhang, Chunyu Wang, Dong Chen, Feng Zhao, Jiaolong Yang, Ting Zhang, Yansong Tang, Yiji Cheng","submitted_at":"2024-07-09T15:14:45Z","abstract_excerpt":"We present RodinHD, which can generate high-fidelity 3D avatars from a portrait image. Existing methods fail to capture intricate details such as hairstyles which we tackle in this paper. We first identify an overlooked problem of catastrophic forgetting that arises when fitting triplanes sequentially on many avatars, caused by the MLP decoder sharing scheme. To overcome this issue, we raise a novel data scheduling strategy and a weight consolidation regularization term, which improves the decoder's capability of rendering sharper details. Additionally, we optimize the guiding effect of the po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06938","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/2407.06938/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":"2407.06938","created_at":"2026-07-05T08:42:39.086881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06938v2","created_at":"2026-07-05T08:42:39.086881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06938","created_at":"2026-07-05T08:42:39.086881+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5JEE6ZC6YQY","created_at":"2026-07-05T08:42:39.086881+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5JEE6ZC6YQY3RJK","created_at":"2026-07-05T08:42:39.086881+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5JEE6ZC","created_at":"2026-07-05T08:42:39.086881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.02777","citing_title":"PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2412.01506","citing_title":"Structured 3D Latents for Scalable and Versatile 3D Generation","ref_index":103,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J5JEE6ZC6YQY3RJKMWLI7RF62D","json":"https://pith.science/pith/J5JEE6ZC6YQY3RJKMWLI7RF62D.json","graph_json":"https://pith.science/api/pith-number/J5JEE6ZC6YQY3RJKMWLI7RF62D/graph.json","events_json":"https://pith.science/api/pith-number/J5JEE6ZC6YQY3RJKMWLI7RF62D/events.json","paper":"https://pith.science/paper/J5JEE6ZC"},"agent_actions":{"view_html":"https://pith.science/pith/J5JEE6ZC6YQY3RJKMWLI7RF62D","download_json":"https://pith.science/pith/J5JEE6ZC6YQY3RJKMWLI7RF62D.json","view_paper":"https://pith.science/paper/J5JEE6ZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06938&json=true","fetch_graph":"https://pith.science/api/pith-number/J5JEE6ZC6YQY3RJKMWLI7RF62D/graph.json","fetch_events":"https://pith.science/api/pith-number/J5JEE6ZC6YQY3RJKMWLI7RF62D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5JEE6ZC6YQY3RJKMWLI7RF62D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5JEE6ZC6YQY3RJKMWLI7RF62D/action/storage_attestation","attest_author":"https://pith.science/pith/J5JEE6ZC6YQY3RJKMWLI7RF62D/action/author_attestation","sign_citation":"https://pith.science/pith/J5JEE6ZC6YQY3RJKMWLI7RF62D/action/citation_signature","submit_replication":"https://pith.science/pith/J5JEE6ZC6YQY3RJKMWLI7RF62D/action/replication_record"}},"created_at":"2026-07-05T08:42:39.086881+00:00","updated_at":"2026-07-05T08:42:39.086881+00:00"}