{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W6ARZAEQGJWKZY7WXMGB2IF553","short_pith_number":"pith:W6ARZAEQ","schema_version":"1.0","canonical_sha256":"b7811c8090326cace3f6bb0c1d20bdeedb96ba7c985756636a8a131068c244c6","source":{"kind":"arxiv","id":"2403.10242","version":2},"attestation_state":"computed","paper":{"title":"GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qijun Feng, Yu-Gang Jiang, Zhen Xing, Zuxuan Wu","submitted_at":"2024-03-15T12:24:36Z","abstract_excerpt":"We introduce GeoGS3D, a novel two-stage framework for reconstructing detailed 3D objects from single-view images. Inspired by the success of pre-trained 2D diffusion models, our method incorporates an orthogonal plane decomposition mechanism to extract 3D geometric features from the 2D input, facilitating the generation of multi-view consistent images. During the following Gaussian Splatting, these images are fused with epipolar attention, fully utilizing the geometric correlations across views. Moreover, we propose a novel metric, Gaussian Divergence Significance (GDS), to prune unnecessary o"},"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":"2403.10242","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T12:24:36Z","cross_cats_sorted":[],"title_canon_sha256":"08a51ef2448e777d6801963d2dd838654a3e1c69afd67c5d80de3d985b9b61f1","abstract_canon_sha256":"b0a7f792b278ed3076516c295f20164e196ca602edfba483adf1abe10615ee91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:48.542504Z","signature_b64":"ZgERgbGExno3kh7Ao+pVLOVnRzpnFOdti+tDV5inSY1lm8ihQMgLX4WB2CVIUh+hwpE2OZXABfKT3NDFeKKOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7811c8090326cace3f6bb0c1d20bdeedb96ba7c985756636a8a131068c244c6","last_reissued_at":"2026-07-05T09:28:48.542004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:48.542004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qijun Feng, Yu-Gang Jiang, Zhen Xing, Zuxuan Wu","submitted_at":"2024-03-15T12:24:36Z","abstract_excerpt":"We introduce GeoGS3D, a novel two-stage framework for reconstructing detailed 3D objects from single-view images. Inspired by the success of pre-trained 2D diffusion models, our method incorporates an orthogonal plane decomposition mechanism to extract 3D geometric features from the 2D input, facilitating the generation of multi-view consistent images. During the following Gaussian Splatting, these images are fused with epipolar attention, fully utilizing the geometric correlations across views. Moreover, we propose a novel metric, Gaussian Divergence Significance (GDS), to prune unnecessary o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10242","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/2403.10242/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":"2403.10242","created_at":"2026-07-05T09:28:48.542063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10242v2","created_at":"2026-07-05T09:28:48.542063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10242","created_at":"2026-07-05T09:28:48.542063+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6ARZAEQGJWK","created_at":"2026-07-05T09:28:48.542063+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6ARZAEQGJWKZY7W","created_at":"2026-07-05T09:28:48.542063+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6ARZAEQ","created_at":"2026-07-05T09:28:48.542063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25975","citing_title":"F-RNG: Feed-Forward Relightable Neural Gaussians","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":213,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13036","citing_title":"Lyra 2.0: Explorable Generative 3D Worlds","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6ARZAEQGJWKZY7WXMGB2IF553","json":"https://pith.science/pith/W6ARZAEQGJWKZY7WXMGB2IF553.json","graph_json":"https://pith.science/api/pith-number/W6ARZAEQGJWKZY7WXMGB2IF553/graph.json","events_json":"https://pith.science/api/pith-number/W6ARZAEQGJWKZY7WXMGB2IF553/events.json","paper":"https://pith.science/paper/W6ARZAEQ"},"agent_actions":{"view_html":"https://pith.science/pith/W6ARZAEQGJWKZY7WXMGB2IF553","download_json":"https://pith.science/pith/W6ARZAEQGJWKZY7WXMGB2IF553.json","view_paper":"https://pith.science/paper/W6ARZAEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10242&json=true","fetch_graph":"https://pith.science/api/pith-number/W6ARZAEQGJWKZY7WXMGB2IF553/graph.json","fetch_events":"https://pith.science/api/pith-number/W6ARZAEQGJWKZY7WXMGB2IF553/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6ARZAEQGJWKZY7WXMGB2IF553/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6ARZAEQGJWKZY7WXMGB2IF553/action/storage_attestation","attest_author":"https://pith.science/pith/W6ARZAEQGJWKZY7WXMGB2IF553/action/author_attestation","sign_citation":"https://pith.science/pith/W6ARZAEQGJWKZY7WXMGB2IF553/action/citation_signature","submit_replication":"https://pith.science/pith/W6ARZAEQGJWKZY7WXMGB2IF553/action/replication_record"}},"created_at":"2026-07-05T09:28:48.542063+00:00","updated_at":"2026-07-05T09:28:48.542063+00:00"}