{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:42CXOTFNWDEJNDUDASJJUUWIO7","short_pith_number":"pith:42CXOTFN","schema_version":"1.0","canonical_sha256":"e685774cadb0c8968e8304929a52c877d636e7ec6a591c4e51a17ddfec0f9850","source":{"kind":"arxiv","id":"2508.16433","version":1},"attestation_state":"computed","paper":{"title":"HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghamen, Gregory Rogez, Matthieu Armando, Philippe Weinzaepfel, Sara Rojas, Vincent Leroy","submitted_at":"2025-08-22T14:43:18Z","abstract_excerpt":"Recovering the 3D geometry of a scene from a sparse set of uncalibrated images is a long-standing problem in computer vision. While recent learning-based approaches such as DUSt3R and MASt3R have demonstrated impressive results by directly predicting dense scene geometry, they are primarily trained on outdoor scenes with static environments and struggle to handle human-centric scenarios. In this work, we introduce HAMSt3R, an extension of MASt3R for joint human and scene 3D reconstruction from sparse, uncalibrated multi-view images. First, we exploit DUNE, a strong image encoder obtained by di"},"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":"2508.16433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-22T14:43:18Z","cross_cats_sorted":[],"title_canon_sha256":"c2b14fa770822b456b5fe89b9a32abf7ef5d623fe3f6e89f6d34c8f5df276eb9","abstract_canon_sha256":"cd8ae53b98f786f7dfe581673f02344b1ee491729888d7de06f9b1c6d76e5d27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:48.198745Z","signature_b64":"gcVMrgKRLcUWda3hRJgmyQgxsRhTXHrco+jsp682YZAFVOfpNghtMmfliGXQj+QUacMW7sPDGBm7PKprfQf6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e685774cadb0c8968e8304929a52c877d636e7ec6a591c4e51a17ddfec0f9850","last_reissued_at":"2026-07-05T11:57:48.198252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:48.198252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghamen, Gregory Rogez, Matthieu Armando, Philippe Weinzaepfel, Sara Rojas, Vincent Leroy","submitted_at":"2025-08-22T14:43:18Z","abstract_excerpt":"Recovering the 3D geometry of a scene from a sparse set of uncalibrated images is a long-standing problem in computer vision. While recent learning-based approaches such as DUSt3R and MASt3R have demonstrated impressive results by directly predicting dense scene geometry, they are primarily trained on outdoor scenes with static environments and struggle to handle human-centric scenarios. In this work, we introduce HAMSt3R, an extension of MASt3R for joint human and scene 3D reconstruction from sparse, uncalibrated multi-view images. First, we exploit DUNE, a strong image encoder obtained by di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16433","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/2508.16433/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":"2508.16433","created_at":"2026-07-05T11:57:48.198320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16433v1","created_at":"2026-07-05T11:57:48.198320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16433","created_at":"2026-07-05T11:57:48.198320+00:00"},{"alias_kind":"pith_short_12","alias_value":"42CXOTFNWDEJ","created_at":"2026-07-05T11:57:48.198320+00:00"},{"alias_kind":"pith_short_16","alias_value":"42CXOTFNWDEJNDUD","created_at":"2026-07-05T11:57:48.198320+00:00"},{"alias_kind":"pith_short_8","alias_value":"42CXOTFN","created_at":"2026-07-05T11:57:48.198320+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24642","citing_title":"Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19923","citing_title":"UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19923","citing_title":"UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42CXOTFNWDEJNDUDASJJUUWIO7","json":"https://pith.science/pith/42CXOTFNWDEJNDUDASJJUUWIO7.json","graph_json":"https://pith.science/api/pith-number/42CXOTFNWDEJNDUDASJJUUWIO7/graph.json","events_json":"https://pith.science/api/pith-number/42CXOTFNWDEJNDUDASJJUUWIO7/events.json","paper":"https://pith.science/paper/42CXOTFN"},"agent_actions":{"view_html":"https://pith.science/pith/42CXOTFNWDEJNDUDASJJUUWIO7","download_json":"https://pith.science/pith/42CXOTFNWDEJNDUDASJJUUWIO7.json","view_paper":"https://pith.science/paper/42CXOTFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16433&json=true","fetch_graph":"https://pith.science/api/pith-number/42CXOTFNWDEJNDUDASJJUUWIO7/graph.json","fetch_events":"https://pith.science/api/pith-number/42CXOTFNWDEJNDUDASJJUUWIO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42CXOTFNWDEJNDUDASJJUUWIO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42CXOTFNWDEJNDUDASJJUUWIO7/action/storage_attestation","attest_author":"https://pith.science/pith/42CXOTFNWDEJNDUDASJJUUWIO7/action/author_attestation","sign_citation":"https://pith.science/pith/42CXOTFNWDEJNDUDASJJUUWIO7/action/citation_signature","submit_replication":"https://pith.science/pith/42CXOTFNWDEJNDUDASJJUUWIO7/action/replication_record"}},"created_at":"2026-07-05T11:57:48.198320+00:00","updated_at":"2026-07-05T11:57:48.198320+00:00"}