{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KPATROHFELAKNXNRFFT4IBG3CB","short_pith_number":"pith:KPATROHF","schema_version":"1.0","canonical_sha256":"53c138b8e522c0a6ddb12967c404db105f3b2ddc0ffe7dfeb517678f328ad280","source":{"kind":"arxiv","id":"2409.03456","version":3},"attestation_state":"computed","paper":{"title":"LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanyang Yu, Ping Tan, Xiaoxiao Long","submitted_at":"2024-09-05T12:09:02Z","abstract_excerpt":"We aim to address sparse-view reconstruction of a 3D scene by leveraging priors from large-scale vision models. While recent advancements such as 3D Gaussian Splatting (3DGS) have demonstrated remarkable successes in 3D reconstruction, these methods typically necessitate hundreds of input images that densely capture the underlying scene, making them time-consuming and impractical for real-world applications. However, sparse-view reconstruction is inherently ill-posed and under-constrained, often resulting in inferior and incomplete outcomes. This is due to issues such as failed initialization,"},"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":"2409.03456","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-05T12:09:02Z","cross_cats_sorted":[],"title_canon_sha256":"32cf38406bc79b71e58aee35e105ef6441bd0190d74719c491bd95af9738051a","abstract_canon_sha256":"0700d8970d4e61c79575fb9e7054a4a71cebc0c38904ed2e7e0b1fa196ecafc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:56.940427Z","signature_b64":"0Gr7rNz5o4CjBh5Vd1vIV0O3zrmW4wfMwPBUUKvbOaPPAZenTbtVp8NCoZeETWBAtOWv0BEHJ0mGKZKlm3C/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53c138b8e522c0a6ddb12967c404db105f3b2ddc0ffe7dfeb517678f328ad280","last_reissued_at":"2026-07-05T11:43:56.939993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:56.939993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanyang Yu, Ping Tan, Xiaoxiao Long","submitted_at":"2024-09-05T12:09:02Z","abstract_excerpt":"We aim to address sparse-view reconstruction of a 3D scene by leveraging priors from large-scale vision models. While recent advancements such as 3D Gaussian Splatting (3DGS) have demonstrated remarkable successes in 3D reconstruction, these methods typically necessitate hundreds of input images that densely capture the underlying scene, making them time-consuming and impractical for real-world applications. However, sparse-view reconstruction is inherently ill-posed and under-constrained, often resulting in inferior and incomplete outcomes. This is due to issues such as failed initialization,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03456","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/2409.03456/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":"2409.03456","created_at":"2026-07-05T11:43:56.940048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03456v3","created_at":"2026-07-05T11:43:56.940048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03456","created_at":"2026-07-05T11:43:56.940048+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPATROHFELAK","created_at":"2026-07-05T11:43:56.940048+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPATROHFELAKNXNR","created_at":"2026-07-05T11:43:56.940048+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPATROHF","created_at":"2026-07-05T11:43:56.940048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13515","citing_title":"MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09688","citing_title":"ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPATROHFELAKNXNRFFT4IBG3CB","json":"https://pith.science/pith/KPATROHFELAKNXNRFFT4IBG3CB.json","graph_json":"https://pith.science/api/pith-number/KPATROHFELAKNXNRFFT4IBG3CB/graph.json","events_json":"https://pith.science/api/pith-number/KPATROHFELAKNXNRFFT4IBG3CB/events.json","paper":"https://pith.science/paper/KPATROHF"},"agent_actions":{"view_html":"https://pith.science/pith/KPATROHFELAKNXNRFFT4IBG3CB","download_json":"https://pith.science/pith/KPATROHFELAKNXNRFFT4IBG3CB.json","view_paper":"https://pith.science/paper/KPATROHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03456&json=true","fetch_graph":"https://pith.science/api/pith-number/KPATROHFELAKNXNRFFT4IBG3CB/graph.json","fetch_events":"https://pith.science/api/pith-number/KPATROHFELAKNXNRFFT4IBG3CB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPATROHFELAKNXNRFFT4IBG3CB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPATROHFELAKNXNRFFT4IBG3CB/action/storage_attestation","attest_author":"https://pith.science/pith/KPATROHFELAKNXNRFFT4IBG3CB/action/author_attestation","sign_citation":"https://pith.science/pith/KPATROHFELAKNXNRFFT4IBG3CB/action/citation_signature","submit_replication":"https://pith.science/pith/KPATROHFELAKNXNRFFT4IBG3CB/action/replication_record"}},"created_at":"2026-07-05T11:43:56.940048+00:00","updated_at":"2026-07-05T11:43:56.940048+00:00"}