{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:USUU62S3Q52JIINCC4GAQJYKDQ","short_pith_number":"pith:USUU62S3","schema_version":"1.0","canonical_sha256":"a4a94f6a5b87749421a2170c08270a1c089c92c8fe884a30b27a2383e29a27ab","source":{"kind":"arxiv","id":"2408.09042","version":1},"attestation_state":"computed","paper":{"title":"ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tang, Matt Feiszli, Pierre Gleize, Weiyao Wang","submitted_at":"2024-08-16T22:45:46Z","abstract_excerpt":"Recovering camera poses from a set of images is a foundational task in 3D computer vision, which powers key applications such as 3D scene/object reconstructions. Classic methods often depend on feature correspondence, such as keypoints, which require the input images to have large overlap and small viewpoint changes. Such requirements present considerable challenges in scenarios with sparse views. Recent data-driven approaches aim to directly output camera poses, either through regressing the 6DoF camera poses or formulating rotation as a probability distribution. However, each approach has it"},"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":"2408.09042","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-16T22:45:46Z","cross_cats_sorted":[],"title_canon_sha256":"8fd5762ae8220ebb6865c6c25c23c7167d2fac774c7a64f2babef6bf1e0ce73a","abstract_canon_sha256":"066fc20f5144c8e993f27c43c6170bb890a83750576587b16c5d7105c03eb815"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:27.191925Z","signature_b64":"e8nPE0DBB/krmhgc632wtYvvsv4fZxN7K7Vpi4y/7GeTbXGXr5nk9kJkSFwzX8qQ139uhvIrys3LOnGDxwyAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4a94f6a5b87749421a2170c08270a1c089c92c8fe884a30b27a2383e29a27ab","last_reissued_at":"2026-07-05T08:56:27.191582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:27.191582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tang, Matt Feiszli, Pierre Gleize, Weiyao Wang","submitted_at":"2024-08-16T22:45:46Z","abstract_excerpt":"Recovering camera poses from a set of images is a foundational task in 3D computer vision, which powers key applications such as 3D scene/object reconstructions. Classic methods often depend on feature correspondence, such as keypoints, which require the input images to have large overlap and small viewpoint changes. Such requirements present considerable challenges in scenarios with sparse views. Recent data-driven approaches aim to directly output camera poses, either through regressing the 6DoF camera poses or formulating rotation as a probability distribution. However, each approach has it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09042","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/2408.09042/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":"2408.09042","created_at":"2026-07-05T08:56:27.191638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09042v1","created_at":"2026-07-05T08:56:27.191638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09042","created_at":"2026-07-05T08:56:27.191638+00:00"},{"alias_kind":"pith_short_12","alias_value":"USUU62S3Q52J","created_at":"2026-07-05T08:56:27.191638+00:00"},{"alias_kind":"pith_short_16","alias_value":"USUU62S3Q52JIINC","created_at":"2026-07-05T08:56:27.191638+00:00"},{"alias_kind":"pith_short_8","alias_value":"USUU62S3","created_at":"2026-07-05T08:56:27.191638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13928","citing_title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/USUU62S3Q52JIINCC4GAQJYKDQ","json":"https://pith.science/pith/USUU62S3Q52JIINCC4GAQJYKDQ.json","graph_json":"https://pith.science/api/pith-number/USUU62S3Q52JIINCC4GAQJYKDQ/graph.json","events_json":"https://pith.science/api/pith-number/USUU62S3Q52JIINCC4GAQJYKDQ/events.json","paper":"https://pith.science/paper/USUU62S3"},"agent_actions":{"view_html":"https://pith.science/pith/USUU62S3Q52JIINCC4GAQJYKDQ","download_json":"https://pith.science/pith/USUU62S3Q52JIINCC4GAQJYKDQ.json","view_paper":"https://pith.science/paper/USUU62S3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09042&json=true","fetch_graph":"https://pith.science/api/pith-number/USUU62S3Q52JIINCC4GAQJYKDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/USUU62S3Q52JIINCC4GAQJYKDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USUU62S3Q52JIINCC4GAQJYKDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USUU62S3Q52JIINCC4GAQJYKDQ/action/storage_attestation","attest_author":"https://pith.science/pith/USUU62S3Q52JIINCC4GAQJYKDQ/action/author_attestation","sign_citation":"https://pith.science/pith/USUU62S3Q52JIINCC4GAQJYKDQ/action/citation_signature","submit_replication":"https://pith.science/pith/USUU62S3Q52JIINCC4GAQJYKDQ/action/replication_record"}},"created_at":"2026-07-05T08:56:27.191638+00:00","updated_at":"2026-07-05T08:56:27.191638+00:00"}