{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FCR73LDPENC2YOWUTO4DREPDP7","short_pith_number":"pith:FCR73LDP","schema_version":"1.0","canonical_sha256":"28a3fdac6f2345ac3ad49bb83891e37fe4f79eeedcff3a702ffa7cc37f8a76f9","source":{"kind":"arxiv","id":"2503.21313","version":2},"attestation_state":"computed","paper":{"title":"HORT: Monocular Hand-held Objects Reconstruction with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Rolandos Alexandros Potamias, Shizhe Chen, Zerui Chen","submitted_at":"2025-03-27T09:45:09Z","abstract_excerpt":"Reconstructing hand-held objects in 3D from monocular images remains a significant challenge in computer vision. Most existing approaches rely on implicit 3D representations, which produce overly smooth reconstructions and are time-consuming to generate explicit 3D shapes. While more recent methods directly reconstruct point clouds with diffusion models, the multi-step denoising makes high-resolution reconstruction inefficient. To address these limitations, we propose a transformer-based model to efficiently reconstruct dense 3D point clouds of hand-held objects. Our method follows a coarse-to"},"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":"2503.21313","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T09:45:09Z","cross_cats_sorted":[],"title_canon_sha256":"df0a9cd1e27fc2faed47cf7ea9f665c93978cc3285e5208c909e4d9f7c1fa313","abstract_canon_sha256":"159505d48b433146b25740ae5a222d8286a4c13df8b3a10ab10f3fdef3668aeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:33.624757Z","signature_b64":"fuXHLsxU8t9DaEbfQsmFaPBRD+pGmNd/x+Vfx63a1Ha6757ZwtejVkg8dSFFwAOz59KzIEYZzOD7LSszpOKJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a3fdac6f2345ac3ad49bb83891e37fe4f79eeedcff3a702ffa7cc37f8a76f9","last_reissued_at":"2026-07-05T11:40:33.624330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:33.624330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HORT: Monocular Hand-held Objects Reconstruction with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Rolandos Alexandros Potamias, Shizhe Chen, Zerui Chen","submitted_at":"2025-03-27T09:45:09Z","abstract_excerpt":"Reconstructing hand-held objects in 3D from monocular images remains a significant challenge in computer vision. Most existing approaches rely on implicit 3D representations, which produce overly smooth reconstructions and are time-consuming to generate explicit 3D shapes. While more recent methods directly reconstruct point clouds with diffusion models, the multi-step denoising makes high-resolution reconstruction inefficient. To address these limitations, we propose a transformer-based model to efficiently reconstruct dense 3D point clouds of hand-held objects. Our method follows a coarse-to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21313","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/2503.21313/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":"2503.21313","created_at":"2026-07-05T11:40:33.624385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21313v2","created_at":"2026-07-05T11:40:33.624385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21313","created_at":"2026-07-05T11:40:33.624385+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCR73LDPENC2","created_at":"2026-07-05T11:40:33.624385+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCR73LDPENC2YOWU","created_at":"2026-07-05T11:40:33.624385+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCR73LDP","created_at":"2026-07-05T11:40:33.624385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07978","citing_title":"One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCR73LDPENC2YOWUTO4DREPDP7","json":"https://pith.science/pith/FCR73LDPENC2YOWUTO4DREPDP7.json","graph_json":"https://pith.science/api/pith-number/FCR73LDPENC2YOWUTO4DREPDP7/graph.json","events_json":"https://pith.science/api/pith-number/FCR73LDPENC2YOWUTO4DREPDP7/events.json","paper":"https://pith.science/paper/FCR73LDP"},"agent_actions":{"view_html":"https://pith.science/pith/FCR73LDPENC2YOWUTO4DREPDP7","download_json":"https://pith.science/pith/FCR73LDPENC2YOWUTO4DREPDP7.json","view_paper":"https://pith.science/paper/FCR73LDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21313&json=true","fetch_graph":"https://pith.science/api/pith-number/FCR73LDPENC2YOWUTO4DREPDP7/graph.json","fetch_events":"https://pith.science/api/pith-number/FCR73LDPENC2YOWUTO4DREPDP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCR73LDPENC2YOWUTO4DREPDP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCR73LDPENC2YOWUTO4DREPDP7/action/storage_attestation","attest_author":"https://pith.science/pith/FCR73LDPENC2YOWUTO4DREPDP7/action/author_attestation","sign_citation":"https://pith.science/pith/FCR73LDPENC2YOWUTO4DREPDP7/action/citation_signature","submit_replication":"https://pith.science/pith/FCR73LDPENC2YOWUTO4DREPDP7/action/replication_record"}},"created_at":"2026-07-05T11:40:33.624385+00:00","updated_at":"2026-07-05T11:40:33.624385+00:00"}