{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AVDQBDSXNOOOOAQCQS4S2WVES7","short_pith_number":"pith:AVDQBDSX","schema_version":"1.0","canonical_sha256":"0547008e576b9ce7020284b92d5aa497e3718f8414a0371328b23367d30d4646","source":{"kind":"arxiv","id":"2506.04908","version":1},"attestation_state":"computed","paper":{"title":"Generating Synthetic Stereo Datasets using 3D Gaussian Splatting and Expert Knowledge Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Filip Slezak, Ivan Nikolov, Joakim B. Haurum, Magnus K. Gjerde, Morten S. Laursen, Thomas B. Moeslund","submitted_at":"2025-06-05T11:41:09Z","abstract_excerpt":"In this paper, we introduce a 3D Gaussian Splatting (3DGS)-based pipeline for stereo dataset generation, offering an efficient alternative to Neural Radiance Fields (NeRF)-based methods. To obtain useful geometry estimates, we explore utilizing the reconstructed geometry from the explicit 3D representations as well as depth estimates from the FoundationStereo model in an expert knowledge transfer setup. We find that when fine-tuning stereo models on 3DGS-generated datasets, we demonstrate competitive performance in zero-shot generalization benchmarks. When using the reconstructed geometry dire"},"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":"2506.04908","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T11:41:09Z","cross_cats_sorted":[],"title_canon_sha256":"d936af70c3241965a78e31cce318ce25fd413a00729c2e18304cfb47dc0f53e2","abstract_canon_sha256":"7efc86054b849f9314d4fd6b49cbd961523430b063d8689ffce381e651fe5aed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:38.833521Z","signature_b64":"zf6yKa7H4S9YKoBfDipZUdaqbwSMbjsfCx/eAkJ5UzRZ/Tvvl8qGjKM7W42szmZGkOqMwxu6HQFTWCgKNK3kCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0547008e576b9ce7020284b92d5aa497e3718f8414a0371328b23367d30d4646","last_reissued_at":"2026-07-05T11:16:38.833024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:38.833024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Synthetic Stereo Datasets using 3D Gaussian Splatting and Expert Knowledge Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Filip Slezak, Ivan Nikolov, Joakim B. Haurum, Magnus K. Gjerde, Morten S. Laursen, Thomas B. Moeslund","submitted_at":"2025-06-05T11:41:09Z","abstract_excerpt":"In this paper, we introduce a 3D Gaussian Splatting (3DGS)-based pipeline for stereo dataset generation, offering an efficient alternative to Neural Radiance Fields (NeRF)-based methods. To obtain useful geometry estimates, we explore utilizing the reconstructed geometry from the explicit 3D representations as well as depth estimates from the FoundationStereo model in an expert knowledge transfer setup. We find that when fine-tuning stereo models on 3DGS-generated datasets, we demonstrate competitive performance in zero-shot generalization benchmarks. When using the reconstructed geometry dire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04908","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/2506.04908/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":"2506.04908","created_at":"2026-07-05T11:16:38.833086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04908v1","created_at":"2026-07-05T11:16:38.833086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04908","created_at":"2026-07-05T11:16:38.833086+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVDQBDSXNOOO","created_at":"2026-07-05T11:16:38.833086+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVDQBDSXNOOOOAQC","created_at":"2026-07-05T11:16:38.833086+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVDQBDSX","created_at":"2026-07-05T11:16:38.833086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AVDQBDSXNOOOOAQCQS4S2WVES7","json":"https://pith.science/pith/AVDQBDSXNOOOOAQCQS4S2WVES7.json","graph_json":"https://pith.science/api/pith-number/AVDQBDSXNOOOOAQCQS4S2WVES7/graph.json","events_json":"https://pith.science/api/pith-number/AVDQBDSXNOOOOAQCQS4S2WVES7/events.json","paper":"https://pith.science/paper/AVDQBDSX"},"agent_actions":{"view_html":"https://pith.science/pith/AVDQBDSXNOOOOAQCQS4S2WVES7","download_json":"https://pith.science/pith/AVDQBDSXNOOOOAQCQS4S2WVES7.json","view_paper":"https://pith.science/paper/AVDQBDSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04908&json=true","fetch_graph":"https://pith.science/api/pith-number/AVDQBDSXNOOOOAQCQS4S2WVES7/graph.json","fetch_events":"https://pith.science/api/pith-number/AVDQBDSXNOOOOAQCQS4S2WVES7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVDQBDSXNOOOOAQCQS4S2WVES7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVDQBDSXNOOOOAQCQS4S2WVES7/action/storage_attestation","attest_author":"https://pith.science/pith/AVDQBDSXNOOOOAQCQS4S2WVES7/action/author_attestation","sign_citation":"https://pith.science/pith/AVDQBDSXNOOOOAQCQS4S2WVES7/action/citation_signature","submit_replication":"https://pith.science/pith/AVDQBDSXNOOOOAQCQS4S2WVES7/action/replication_record"}},"created_at":"2026-07-05T11:16:38.833086+00:00","updated_at":"2026-07-05T11:16:38.833086+00:00"}