{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AHGC36FX3CN3HCEXJ5UYMLS5JM","short_pith_number":"pith:AHGC36FX","schema_version":"1.0","canonical_sha256":"01cc2df8b7d89bb388974f69862e5d4b281ae003bbde9194fd31d3e4ee116a71","source":{"kind":"arxiv","id":"2507.08136","version":2},"attestation_state":"computed","paper":{"title":"RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beizhen Zhao, Chong Cheng, Hao Wang, Sicheng Yu, Yu Hu, Zijian Wang","submitted_at":"2025-07-10T19:56:08Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has demonstrated its potential in reconstructing scenes from unposed images. However, optimization-based 3DGS methods struggle with sparse views due to limited prior knowledge. Meanwhile, feed-forward Gaussian approaches are constrained by input formats, making it challenging to incorporate more input views. To address these challenges, we propose RegGS, a 3D Gaussian registration-based framework for reconstructing unposed sparse views. RegGS aligns local 3D Gaussians generated by a feed-forward network into a globally consistent 3D Gaussian representation. Technic"},"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":"2507.08136","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T19:56:08Z","cross_cats_sorted":[],"title_canon_sha256":"b9dbdd4c0fd94d3b73260bc4b8897c65a7062992b387688e833f059c6ab6b62a","abstract_canon_sha256":"53ebca89dfababa2237335d2424c8186f5132483b362a39625077e544b17fe7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:56.479699Z","signature_b64":"eeUFgTsoz0p3HUnmnRAtsbC9K1QL+sLZBOjyq+m1NAFnVMaExisa4tV3JwlMCahkTEN/OJk6S8pmGUyydS3tDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01cc2df8b7d89bb388974f69862e5d4b281ae003bbde9194fd31d3e4ee116a71","last_reissued_at":"2026-07-05T11:39:56.479235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:56.479235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beizhen Zhao, Chong Cheng, Hao Wang, Sicheng Yu, Yu Hu, Zijian Wang","submitted_at":"2025-07-10T19:56:08Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has demonstrated its potential in reconstructing scenes from unposed images. However, optimization-based 3DGS methods struggle with sparse views due to limited prior knowledge. Meanwhile, feed-forward Gaussian approaches are constrained by input formats, making it challenging to incorporate more input views. To address these challenges, we propose RegGS, a 3D Gaussian registration-based framework for reconstructing unposed sparse views. RegGS aligns local 3D Gaussians generated by a feed-forward network into a globally consistent 3D Gaussian representation. Technic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08136","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/2507.08136/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":"2507.08136","created_at":"2026-07-05T11:39:56.479291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08136v2","created_at":"2026-07-05T11:39:56.479291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08136","created_at":"2026-07-05T11:39:56.479291+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHGC36FX3CN3","created_at":"2026-07-05T11:39:56.479291+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHGC36FX3CN3HCEX","created_at":"2026-07-05T11:39:56.479291+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHGC36FX","created_at":"2026-07-05T11:39:56.479291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23889","citing_title":"HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHGC36FX3CN3HCEXJ5UYMLS5JM","json":"https://pith.science/pith/AHGC36FX3CN3HCEXJ5UYMLS5JM.json","graph_json":"https://pith.science/api/pith-number/AHGC36FX3CN3HCEXJ5UYMLS5JM/graph.json","events_json":"https://pith.science/api/pith-number/AHGC36FX3CN3HCEXJ5UYMLS5JM/events.json","paper":"https://pith.science/paper/AHGC36FX"},"agent_actions":{"view_html":"https://pith.science/pith/AHGC36FX3CN3HCEXJ5UYMLS5JM","download_json":"https://pith.science/pith/AHGC36FX3CN3HCEXJ5UYMLS5JM.json","view_paper":"https://pith.science/paper/AHGC36FX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08136&json=true","fetch_graph":"https://pith.science/api/pith-number/AHGC36FX3CN3HCEXJ5UYMLS5JM/graph.json","fetch_events":"https://pith.science/api/pith-number/AHGC36FX3CN3HCEXJ5UYMLS5JM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHGC36FX3CN3HCEXJ5UYMLS5JM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHGC36FX3CN3HCEXJ5UYMLS5JM/action/storage_attestation","attest_author":"https://pith.science/pith/AHGC36FX3CN3HCEXJ5UYMLS5JM/action/author_attestation","sign_citation":"https://pith.science/pith/AHGC36FX3CN3HCEXJ5UYMLS5JM/action/citation_signature","submit_replication":"https://pith.science/pith/AHGC36FX3CN3HCEXJ5UYMLS5JM/action/replication_record"}},"created_at":"2026-07-05T11:39:56.479291+00:00","updated_at":"2026-07-05T11:39:56.479291+00:00"}