{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:655KM6QFCLX5ZTKYWEJCRFDGP2","short_pith_number":"pith:655KM6QF","schema_version":"1.0","canonical_sha256":"f77aa67a0512efdccd58b1122894667e8c6ae98fa5b267a9345bb85058b341e2","source":{"kind":"arxiv","id":"2411.16779","version":1},"attestation_state":"computed","paper":{"title":"NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiale Xu, Jinpeng Liu, Weihao Cheng, Xintao Wang, Yansong Tang, Yiming Gao, Ying Shan","submitted_at":"2024-11-25T07:57:17Z","abstract_excerpt":"We introduce NovelGS, a diffusion model for Gaussian Splatting (GS) given sparse-view images. Recent works leverage feed-forward networks to generate pixel-aligned Gaussians, which could be fast rendered. Unfortunately, the method was unable to produce satisfactory results for areas not covered by the input images due to the formulation of these methods. In contrast, we leverage the novel view denoising through a transformer-based network to generate 3D Gaussians. Specifically, by incorporating both conditional views and noisy target views, the network predicts pixel-aligned Gaussians for each"},"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":"2411.16779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T07:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"22df1d41f44f768b1c74ca443b42ff3cfa797dd837874edf59b21e6fdff9e593","abstract_canon_sha256":"62e4f4b09475a9bef7f85e40e8392e7d971c96b12e0a046f555e0f2cf858698d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:23.009655Z","signature_b64":"D7gtYEZ1lgp/4SWqe08xzDgA17KAHDBu14OcxmiN85n3z1YfASHLwPiGlPtSiz0dcUX5zj9ak+MhnJzMXAkRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f77aa67a0512efdccd58b1122894667e8c6ae98fa5b267a9345bb85058b341e2","last_reissued_at":"2026-07-05T09:40:23.009265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:23.009265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiale Xu, Jinpeng Liu, Weihao Cheng, Xintao Wang, Yansong Tang, Yiming Gao, Ying Shan","submitted_at":"2024-11-25T07:57:17Z","abstract_excerpt":"We introduce NovelGS, a diffusion model for Gaussian Splatting (GS) given sparse-view images. Recent works leverage feed-forward networks to generate pixel-aligned Gaussians, which could be fast rendered. Unfortunately, the method was unable to produce satisfactory results for areas not covered by the input images due to the formulation of these methods. In contrast, we leverage the novel view denoising through a transformer-based network to generate 3D Gaussians. Specifically, by incorporating both conditional views and noisy target views, the network predicts pixel-aligned Gaussians for each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16779","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/2411.16779/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":"2411.16779","created_at":"2026-07-05T09:40:23.009322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16779v1","created_at":"2026-07-05T09:40:23.009322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16779","created_at":"2026-07-05T09:40:23.009322+00:00"},{"alias_kind":"pith_short_12","alias_value":"655KM6QFCLX5","created_at":"2026-07-05T09:40:23.009322+00:00"},{"alias_kind":"pith_short_16","alias_value":"655KM6QFCLX5ZTKY","created_at":"2026-07-05T09:40:23.009322+00:00"},{"alias_kind":"pith_short_8","alias_value":"655KM6QF","created_at":"2026-07-05T09:40:23.009322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20872","citing_title":"CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":217,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/655KM6QFCLX5ZTKYWEJCRFDGP2","json":"https://pith.science/pith/655KM6QFCLX5ZTKYWEJCRFDGP2.json","graph_json":"https://pith.science/api/pith-number/655KM6QFCLX5ZTKYWEJCRFDGP2/graph.json","events_json":"https://pith.science/api/pith-number/655KM6QFCLX5ZTKYWEJCRFDGP2/events.json","paper":"https://pith.science/paper/655KM6QF"},"agent_actions":{"view_html":"https://pith.science/pith/655KM6QFCLX5ZTKYWEJCRFDGP2","download_json":"https://pith.science/pith/655KM6QFCLX5ZTKYWEJCRFDGP2.json","view_paper":"https://pith.science/paper/655KM6QF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16779&json=true","fetch_graph":"https://pith.science/api/pith-number/655KM6QFCLX5ZTKYWEJCRFDGP2/graph.json","fetch_events":"https://pith.science/api/pith-number/655KM6QFCLX5ZTKYWEJCRFDGP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/655KM6QFCLX5ZTKYWEJCRFDGP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/655KM6QFCLX5ZTKYWEJCRFDGP2/action/storage_attestation","attest_author":"https://pith.science/pith/655KM6QFCLX5ZTKYWEJCRFDGP2/action/author_attestation","sign_citation":"https://pith.science/pith/655KM6QFCLX5ZTKYWEJCRFDGP2/action/citation_signature","submit_replication":"https://pith.science/pith/655KM6QFCLX5ZTKYWEJCRFDGP2/action/replication_record"}},"created_at":"2026-07-05T09:40:23.009322+00:00","updated_at":"2026-07-05T09:40:23.009322+00:00"}