{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IBNTYOWBETUHOGSI6HVYHRXNYZ","short_pith_number":"pith:IBNTYOWB","schema_version":"1.0","canonical_sha256":"405b3c3ac124e8771a48f1eb83c6edc65cc7e01d6374eab0c66461edd9a216ca","source":{"kind":"arxiv","id":"2510.13310","version":3},"attestation_state":"computed","paper":{"title":"InstantSfM: Towards GPU-Native SfM for the Deep Learning Era","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wang, Haozhe Lou, Jiageng Mao, Jiankun Zhong, Quankai Gao, Ulrich Neumann, Yue Wang, Zitong Zhan, Ziyu Chen","submitted_at":"2025-10-15T08:58:05Z","abstract_excerpt":"Structure-from-Motion (SfM) is a fundamental technique for recovering camera poses and scene structure from multi-view imagery, serving as a critical upstream component for applications ranging from 3D reconstruction to modern neural scene representations such as 3D Gaussian Splatting. However, most mature SfM systems remain CPU-centric and built upon traditional optimization toolchains, creating a growing mismatch with modern GPU-based, learning-driven pipelines and limiting scalability in large-scale scenes. While recent advances in GPU-accelerated bundle adjustment (BA) have demonstrated th"},"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":"2510.13310","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-15T08:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"a5d39e1076c0ac26458f5dc9eda1136603f8be157c3bcc0002bc68d08648962f","abstract_canon_sha256":"16a40b1adda9d8c1a6edec1aa34cf2207eb4171afa4fbbaa85e290597e7a4b76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T00:23:36.392657Z","signature_b64":"iEZU4ec4TZ+Ui3xQKADX9ailfJLh+reXV9TID+aXh7DW1eKmeEh5oo+w6KEDC7IZaAa26Dad8WQdN5vaZmOVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"405b3c3ac124e8771a48f1eb83c6edc65cc7e01d6374eab0c66461edd9a216ca","last_reissued_at":"2026-07-23T00:23:36.391798Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T00:23:36.391798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstantSfM: Towards GPU-Native SfM for the Deep Learning Era","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wang, Haozhe Lou, Jiageng Mao, Jiankun Zhong, Quankai Gao, Ulrich Neumann, Yue Wang, Zitong Zhan, Ziyu Chen","submitted_at":"2025-10-15T08:58:05Z","abstract_excerpt":"Structure-from-Motion (SfM) is a fundamental technique for recovering camera poses and scene structure from multi-view imagery, serving as a critical upstream component for applications ranging from 3D reconstruction to modern neural scene representations such as 3D Gaussian Splatting. However, most mature SfM systems remain CPU-centric and built upon traditional optimization toolchains, creating a growing mismatch with modern GPU-based, learning-driven pipelines and limiting scalability in large-scale scenes. While recent advances in GPU-accelerated bundle adjustment (BA) have demonstrated th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.13310","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/2510.13310/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":"2510.13310","created_at":"2026-07-23T00:23:36.392193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.13310v3","created_at":"2026-07-23T00:23:36.392193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.13310","created_at":"2026-07-23T00:23:36.392193+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBNTYOWBETUH","created_at":"2026-07-23T00:23:36.392193+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBNTYOWBETUHOGSI","created_at":"2026-07-23T00:23:36.392193+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBNTYOWB","created_at":"2026-07-23T00:23:36.392193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00579","citing_title":"EPO: Boosting 3D Foundation Models with Edge-based Pose Optimization","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBNTYOWBETUHOGSI6HVYHRXNYZ","json":"https://pith.science/pith/IBNTYOWBETUHOGSI6HVYHRXNYZ.json","graph_json":"https://pith.science/api/pith-number/IBNTYOWBETUHOGSI6HVYHRXNYZ/graph.json","events_json":"https://pith.science/api/pith-number/IBNTYOWBETUHOGSI6HVYHRXNYZ/events.json","paper":"https://pith.science/paper/IBNTYOWB"},"agent_actions":{"view_html":"https://pith.science/pith/IBNTYOWBETUHOGSI6HVYHRXNYZ","download_json":"https://pith.science/pith/IBNTYOWBETUHOGSI6HVYHRXNYZ.json","view_paper":"https://pith.science/paper/IBNTYOWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.13310&json=true","fetch_graph":"https://pith.science/api/pith-number/IBNTYOWBETUHOGSI6HVYHRXNYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IBNTYOWBETUHOGSI6HVYHRXNYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBNTYOWBETUHOGSI6HVYHRXNYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBNTYOWBETUHOGSI6HVYHRXNYZ/action/storage_attestation","attest_author":"https://pith.science/pith/IBNTYOWBETUHOGSI6HVYHRXNYZ/action/author_attestation","sign_citation":"https://pith.science/pith/IBNTYOWBETUHOGSI6HVYHRXNYZ/action/citation_signature","submit_replication":"https://pith.science/pith/IBNTYOWBETUHOGSI6HVYHRXNYZ/action/replication_record"}},"created_at":"2026-07-23T00:23:36.392193+00:00","updated_at":"2026-07-23T00:23:36.392193+00:00"}