{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MVQGJHN3SY3GZP3Q5U2KTGXL5S","short_pith_number":"pith:MVQGJHN3","schema_version":"1.0","canonical_sha256":"6560649dbb96366cbf70ed34a99aebec9fce86635ebc7a35d2ad43364dca7162","source":{"kind":"arxiv","id":"2502.17377","version":1},"attestation_state":"computed","paper":{"title":"Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Cheng, Gangjian Zhang, Gaochao Song, Hao Wang, Qinzheng Zhou, Yiyang Yao","submitted_at":"2025-02-24T17:59:08Z","abstract_excerpt":"This paper investigates an open research challenge of reconstructing high-quality, large 3D open scenes from images. It is observed existing methods have various limitations, such as requiring precise camera poses for input and dense viewpoints for supervision. To perform effective and efficient 3D scene reconstruction, we propose a novel graph-guided 3D scene reconstruction framework, GraphGS. Specifically, given a set of images captured by RGB cameras on a scene, we first design a spatial prior-based scene structure estimation method. This is then used to create a camera graph that includes "},"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":"2502.17377","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T17:59:08Z","cross_cats_sorted":[],"title_canon_sha256":"ae1fe08c08ec5ac9a75d9e4ef3457573e06039e3f292dfe5480ee186819abd14","abstract_canon_sha256":"a8bd7f717ae89a9babebcda48a2f00cbd3471c6d83a6cb1711e6aefe04789f14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:09.459341Z","signature_b64":"OTTwvHT15vlqBYGecMTl/j3Dq1xR7yQcoKe9CZ/NonaNI/4YIv9ppmcoamsDUWKiTZiP2hQfKt/+OZNzXsWmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6560649dbb96366cbf70ed34a99aebec9fce86635ebc7a35d2ad43364dca7162","last_reissued_at":"2026-07-05T10:19:09.458852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:09.458852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Cheng, Gangjian Zhang, Gaochao Song, Hao Wang, Qinzheng Zhou, Yiyang Yao","submitted_at":"2025-02-24T17:59:08Z","abstract_excerpt":"This paper investigates an open research challenge of reconstructing high-quality, large 3D open scenes from images. It is observed existing methods have various limitations, such as requiring precise camera poses for input and dense viewpoints for supervision. To perform effective and efficient 3D scene reconstruction, we propose a novel graph-guided 3D scene reconstruction framework, GraphGS. Specifically, given a set of images captured by RGB cameras on a scene, we first design a spatial prior-based scene structure estimation method. This is then used to create a camera graph that includes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17377","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/2502.17377/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":"2502.17377","created_at":"2026-07-05T10:19:09.458914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17377v1","created_at":"2026-07-05T10:19:09.458914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17377","created_at":"2026-07-05T10:19:09.458914+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVQGJHN3SY3G","created_at":"2026-07-05T10:19:09.458914+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVQGJHN3SY3GZP3Q","created_at":"2026-07-05T10:19:09.458914+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVQGJHN3","created_at":"2026-07-05T10:19:09.458914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23555","citing_title":"Generator-Refiner-Examiner: A Tri-Module Data Augmentation Framework for 3D Human Avatar Learning from Monocular Videos","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23889","citing_title":"HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVQGJHN3SY3GZP3Q5U2KTGXL5S","json":"https://pith.science/pith/MVQGJHN3SY3GZP3Q5U2KTGXL5S.json","graph_json":"https://pith.science/api/pith-number/MVQGJHN3SY3GZP3Q5U2KTGXL5S/graph.json","events_json":"https://pith.science/api/pith-number/MVQGJHN3SY3GZP3Q5U2KTGXL5S/events.json","paper":"https://pith.science/paper/MVQGJHN3"},"agent_actions":{"view_html":"https://pith.science/pith/MVQGJHN3SY3GZP3Q5U2KTGXL5S","download_json":"https://pith.science/pith/MVQGJHN3SY3GZP3Q5U2KTGXL5S.json","view_paper":"https://pith.science/paper/MVQGJHN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17377&json=true","fetch_graph":"https://pith.science/api/pith-number/MVQGJHN3SY3GZP3Q5U2KTGXL5S/graph.json","fetch_events":"https://pith.science/api/pith-number/MVQGJHN3SY3GZP3Q5U2KTGXL5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVQGJHN3SY3GZP3Q5U2KTGXL5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVQGJHN3SY3GZP3Q5U2KTGXL5S/action/storage_attestation","attest_author":"https://pith.science/pith/MVQGJHN3SY3GZP3Q5U2KTGXL5S/action/author_attestation","sign_citation":"https://pith.science/pith/MVQGJHN3SY3GZP3Q5U2KTGXL5S/action/citation_signature","submit_replication":"https://pith.science/pith/MVQGJHN3SY3GZP3Q5U2KTGXL5S/action/replication_record"}},"created_at":"2026-07-05T10:19:09.458914+00:00","updated_at":"2026-07-05T10:19:09.458914+00:00"}