{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QPKFRM5KK6IIKJQOX4HQYYYGQT","short_pith_number":"pith:QPKFRM5K","schema_version":"1.0","canonical_sha256":"83d458b3aa579085260ebf0f0c630684f9724da5d6efdcff649457769ea34126","source":{"kind":"arxiv","id":"2501.04689","version":1},"attestation_state":"computed","paper":{"title":"SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Aaryaman Vasishta, James M. Rehg, Mark Boss, Varun Jampani, Zixuan Huang","submitted_at":"2025-01-08T18:52:03Z","abstract_excerpt":"We study the problem of single-image 3D object reconstruction. Recent works have diverged into two directions: regression-based modeling and generative modeling. Regression methods efficiently infer visible surfaces, but struggle with occluded regions. Generative methods handle uncertain regions better by modeling distributions, but are computationally expensive and the generation is often misaligned with visible surfaces. In this paper, we present SPAR3D, a novel two-stage approach aiming to take the best of both directions. The first stage of SPAR3D generates sparse 3D point clouds using a l"},"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":"2501.04689","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T18:52:03Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"6bd0b8923ebd1b2d9596176dd9129e774d20a88f85a54f281a1c9614c100b8db","abstract_canon_sha256":"ce9f8cfd6ddb990db69db4a705ff48620516ad2a9e60b79af301d0ec69300371"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:38.842230Z","signature_b64":"pCGZzatKiD8EoRb8fNL73fS1mhquliYsDvWvIE0HiNtKUZvfaUXwZMHjSXglGPEWzRTEkCN3VrUVlbDAENfCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83d458b3aa579085260ebf0f0c630684f9724da5d6efdcff649457769ea34126","last_reissued_at":"2026-07-05T09:58:38.841781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:38.841781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Aaryaman Vasishta, James M. Rehg, Mark Boss, Varun Jampani, Zixuan Huang","submitted_at":"2025-01-08T18:52:03Z","abstract_excerpt":"We study the problem of single-image 3D object reconstruction. Recent works have diverged into two directions: regression-based modeling and generative modeling. Regression methods efficiently infer visible surfaces, but struggle with occluded regions. Generative methods handle uncertain regions better by modeling distributions, but are computationally expensive and the generation is often misaligned with visible surfaces. In this paper, we present SPAR3D, a novel two-stage approach aiming to take the best of both directions. The first stage of SPAR3D generates sparse 3D point clouds using a l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04689","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/2501.04689/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":"2501.04689","created_at":"2026-07-05T09:58:38.841837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04689v1","created_at":"2026-07-05T09:58:38.841837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04689","created_at":"2026-07-05T09:58:38.841837+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPKFRM5KK6II","created_at":"2026-07-05T09:58:38.841837+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPKFRM5KK6IIKJQO","created_at":"2026-07-05T09:58:38.841837+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPKFRM5K","created_at":"2026-07-05T09:58:38.841837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06565","citing_title":"ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation","ref_index":96,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23514","citing_title":"Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17092","citing_title":"SPAGS: Sparse-View Articulated Object Reconstruction from Single State via Planar Gaussian Splatting","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07834","citing_title":"Voxify3D: Pixel Art Meets Volumetric Rendering","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11633","citing_title":"MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPKFRM5KK6IIKJQOX4HQYYYGQT","json":"https://pith.science/pith/QPKFRM5KK6IIKJQOX4HQYYYGQT.json","graph_json":"https://pith.science/api/pith-number/QPKFRM5KK6IIKJQOX4HQYYYGQT/graph.json","events_json":"https://pith.science/api/pith-number/QPKFRM5KK6IIKJQOX4HQYYYGQT/events.json","paper":"https://pith.science/paper/QPKFRM5K"},"agent_actions":{"view_html":"https://pith.science/pith/QPKFRM5KK6IIKJQOX4HQYYYGQT","download_json":"https://pith.science/pith/QPKFRM5KK6IIKJQOX4HQYYYGQT.json","view_paper":"https://pith.science/paper/QPKFRM5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04689&json=true","fetch_graph":"https://pith.science/api/pith-number/QPKFRM5KK6IIKJQOX4HQYYYGQT/graph.json","fetch_events":"https://pith.science/api/pith-number/QPKFRM5KK6IIKJQOX4HQYYYGQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPKFRM5KK6IIKJQOX4HQYYYGQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPKFRM5KK6IIKJQOX4HQYYYGQT/action/storage_attestation","attest_author":"https://pith.science/pith/QPKFRM5KK6IIKJQOX4HQYYYGQT/action/author_attestation","sign_citation":"https://pith.science/pith/QPKFRM5KK6IIKJQOX4HQYYYGQT/action/citation_signature","submit_replication":"https://pith.science/pith/QPKFRM5KK6IIKJQOX4HQYYYGQT/action/replication_record"}},"created_at":"2026-07-05T09:58:38.841837+00:00","updated_at":"2026-07-05T09:58:38.841837+00:00"}