{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NJMNG4TFX7RVJC2J3LHLSU7KCK","short_pith_number":"pith:NJMNG4TF","schema_version":"1.0","canonical_sha256":"6a58d37265bfe3548b49daceb953ea12829aa1e952f0b81b370829ce518b30ef","source":{"kind":"arxiv","id":"2412.10209","version":2},"attestation_state":"computed","paper":{"title":"GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Davide Davoli, Jiapeng Tang, Liam Schoneveld, Matthias Niessner, Tobias Kirschstein","submitted_at":"2024-12-13T15:31:22Z","abstract_excerpt":"We propose a novel approach for reconstructing animatable 3D Gaussian avatars from monocular videos captured by commodity devices like smartphones. Photorealistic 3D head avatar reconstruction from such recordings is challenging due to limited observations, which leaves unobserved regions under-constrained and can lead to artifacts in novel views. To address this problem, we introduce a multi-view head diffusion model, leveraging its priors to fill in missing regions and ensure view consistency in Gaussian splatting renderings. To enable precise viewpoint control, we use normal maps rendered f"},"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":"2412.10209","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T15:31:22Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"31696115f7b7e300de88b9087e6d1bd7e41936b407008af32b5f3cbce6308f6d","abstract_canon_sha256":"43cbd6f80941b97f21e1501cfae1905cfb3fdb0bdbeb99aa2fc453a964fa098d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:57.588268Z","signature_b64":"GjzPmA+dV4EycaSf3DSXtwB2Z0T++TuQr0m/EcSeq3HzitTFkKOmPgQpDVADkaQHdRRoGfMf3g0inIEbZnWZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a58d37265bfe3548b49daceb953ea12829aa1e952f0b81b370829ce518b30ef","last_reissued_at":"2026-07-05T10:48:57.587789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:57.587789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Davide Davoli, Jiapeng Tang, Liam Schoneveld, Matthias Niessner, Tobias Kirschstein","submitted_at":"2024-12-13T15:31:22Z","abstract_excerpt":"We propose a novel approach for reconstructing animatable 3D Gaussian avatars from monocular videos captured by commodity devices like smartphones. Photorealistic 3D head avatar reconstruction from such recordings is challenging due to limited observations, which leaves unobserved regions under-constrained and can lead to artifacts in novel views. To address this problem, we introduce a multi-view head diffusion model, leveraging its priors to fill in missing regions and ensure view consistency in Gaussian splatting renderings. To enable precise viewpoint control, we use normal maps rendered f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10209","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/2412.10209/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":"2412.10209","created_at":"2026-07-05T10:48:57.587840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10209v2","created_at":"2026-07-05T10:48:57.587840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10209","created_at":"2026-07-05T10:48:57.587840+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJMNG4TFX7RV","created_at":"2026-07-05T10:48:57.587840+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJMNG4TFX7RVJC2J","created_at":"2026-07-05T10:48:57.587840+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJMNG4TF","created_at":"2026-07-05T10:48:57.587840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05912","citing_title":"Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04787","citing_title":"AvatarPointillist: AutoRegressive 4D Gaussian Avatarization","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NJMNG4TFX7RVJC2J3LHLSU7KCK","json":"https://pith.science/pith/NJMNG4TFX7RVJC2J3LHLSU7KCK.json","graph_json":"https://pith.science/api/pith-number/NJMNG4TFX7RVJC2J3LHLSU7KCK/graph.json","events_json":"https://pith.science/api/pith-number/NJMNG4TFX7RVJC2J3LHLSU7KCK/events.json","paper":"https://pith.science/paper/NJMNG4TF"},"agent_actions":{"view_html":"https://pith.science/pith/NJMNG4TFX7RVJC2J3LHLSU7KCK","download_json":"https://pith.science/pith/NJMNG4TFX7RVJC2J3LHLSU7KCK.json","view_paper":"https://pith.science/paper/NJMNG4TF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10209&json=true","fetch_graph":"https://pith.science/api/pith-number/NJMNG4TFX7RVJC2J3LHLSU7KCK/graph.json","fetch_events":"https://pith.science/api/pith-number/NJMNG4TFX7RVJC2J3LHLSU7KCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJMNG4TFX7RVJC2J3LHLSU7KCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJMNG4TFX7RVJC2J3LHLSU7KCK/action/storage_attestation","attest_author":"https://pith.science/pith/NJMNG4TFX7RVJC2J3LHLSU7KCK/action/author_attestation","sign_citation":"https://pith.science/pith/NJMNG4TFX7RVJC2J3LHLSU7KCK/action/citation_signature","submit_replication":"https://pith.science/pith/NJMNG4TFX7RVJC2J3LHLSU7KCK/action/replication_record"}},"created_at":"2026-07-05T10:48:57.587840+00:00","updated_at":"2026-07-05T10:48:57.587840+00:00"}