{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OB7J6PTGDHIWLYTM7NRU7MWWLE","short_pith_number":"pith:OB7J6PTG","schema_version":"1.0","canonical_sha256":"707e9f3e6619d165e26cfb634fb2d6590655630845c0fb8f751c768eaf43e6a6","source":{"kind":"arxiv","id":"2507.23597","version":3},"attestation_state":"computed","paper":{"title":"MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Jie Song, Longteng Duan, Michael J. Black, Zijian Dong","submitted_at":"2025-07-31T14:36:24Z","abstract_excerpt":"We present MoGA, a novel method to reconstruct high-fidelity 3D Gaussian avatars from a single-view image. The main challenge lies in inferring unseen appearance and geometric details while ensuring 3D consistency and realism. Most previous methods rely on 2D diffusion models to synthesize unseen views; however, these generated views are sparse and inconsistent, resulting in unrealistic 3D artifacts and blurred appearance. To address these limitations, we leverage a generative avatar model, that can generate diverse 3D avatars by sampling deformed Gaussians from a learned prior distribution. D"},"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":"2507.23597","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T14:36:24Z","cross_cats_sorted":[],"title_canon_sha256":"6d064787f11fc7fdf4dfdfad792b71ce8a997e255003f6ca1c0708218629ffcc","abstract_canon_sha256":"d9e4737a62af36607da343ee8c886db8212e6df5858e2f7213970b384511f38d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:33.181821Z","signature_b64":"jsoJDOzoCjOVDY9UwGlFXuqiEQH9WQgsc++e3AKS47zEuVqMlUWSUVTva8haKIWizSgSGAMPsf5o72X4ansXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"707e9f3e6619d165e26cfb634fb2d6590655630845c0fb8f751c768eaf43e6a6","last_reissued_at":"2026-07-05T11:51:33.181295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:33.181295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Jie Song, Longteng Duan, Michael J. Black, Zijian Dong","submitted_at":"2025-07-31T14:36:24Z","abstract_excerpt":"We present MoGA, a novel method to reconstruct high-fidelity 3D Gaussian avatars from a single-view image. The main challenge lies in inferring unseen appearance and geometric details while ensuring 3D consistency and realism. Most previous methods rely on 2D diffusion models to synthesize unseen views; however, these generated views are sparse and inconsistent, resulting in unrealistic 3D artifacts and blurred appearance. To address these limitations, we leverage a generative avatar model, that can generate diverse 3D avatars by sampling deformed Gaussians from a learned prior distribution. D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23597","kind":"arxiv","version":3},"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/2507.23597/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":"2507.23597","created_at":"2026-07-05T11:51:33.181370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23597v3","created_at":"2026-07-05T11:51:33.181370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23597","created_at":"2026-07-05T11:51:33.181370+00:00"},{"alias_kind":"pith_short_12","alias_value":"OB7J6PTGDHIW","created_at":"2026-07-05T11:51:33.181370+00:00"},{"alias_kind":"pith_short_16","alias_value":"OB7J6PTGDHIWLYTM","created_at":"2026-07-05T11:51:33.181370+00:00"},{"alias_kind":"pith_short_8","alias_value":"OB7J6PTG","created_at":"2026-07-05T11:51:33.181370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02883","citing_title":"Information-Regularized Constrained Inversion for Stable Avatar Editing from Sparse Supervision","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OB7J6PTGDHIWLYTM7NRU7MWWLE","json":"https://pith.science/pith/OB7J6PTGDHIWLYTM7NRU7MWWLE.json","graph_json":"https://pith.science/api/pith-number/OB7J6PTGDHIWLYTM7NRU7MWWLE/graph.json","events_json":"https://pith.science/api/pith-number/OB7J6PTGDHIWLYTM7NRU7MWWLE/events.json","paper":"https://pith.science/paper/OB7J6PTG"},"agent_actions":{"view_html":"https://pith.science/pith/OB7J6PTGDHIWLYTM7NRU7MWWLE","download_json":"https://pith.science/pith/OB7J6PTGDHIWLYTM7NRU7MWWLE.json","view_paper":"https://pith.science/paper/OB7J6PTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23597&json=true","fetch_graph":"https://pith.science/api/pith-number/OB7J6PTGDHIWLYTM7NRU7MWWLE/graph.json","fetch_events":"https://pith.science/api/pith-number/OB7J6PTGDHIWLYTM7NRU7MWWLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OB7J6PTGDHIWLYTM7NRU7MWWLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OB7J6PTGDHIWLYTM7NRU7MWWLE/action/storage_attestation","attest_author":"https://pith.science/pith/OB7J6PTGDHIWLYTM7NRU7MWWLE/action/author_attestation","sign_citation":"https://pith.science/pith/OB7J6PTGDHIWLYTM7NRU7MWWLE/action/citation_signature","submit_replication":"https://pith.science/pith/OB7J6PTGDHIWLYTM7NRU7MWWLE/action/replication_record"}},"created_at":"2026-07-05T11:51:33.181370+00:00","updated_at":"2026-07-05T11:51:33.181370+00:00"}