{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VY5BZUDIQD5CW5ZKZCCRG7R2PK","short_pith_number":"pith:VY5BZUDI","schema_version":"1.0","canonical_sha256":"ae3a1cd06880fa2b772ac885137e3a7aa4259616ca0d5a78baf98b0493255c62","source":{"kind":"arxiv","id":"2106.01178","version":3},"attestation_state":"computed","paper":{"title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Vorontsova, Anton Konushin, Danila Rukhovich","submitted_at":"2021-06-02T14:20:24Z","abstract_excerpt":"In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem. To address this problem, we propose ImVoxelNet, a novel fully convolutional method of 3D object detection based on monocular or multi-view RGB images. The number of monocular images in each multi-view input can variate during training and inference; actually, this number might be unique for each multi-view input. ImVoxelNet successfully handles both indoor and outdoor scenes, which makes it general-purpose. Specifically, it achieves state-of-the-art results in car detection o"},"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":"2106.01178","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-02T14:20:24Z","cross_cats_sorted":[],"title_canon_sha256":"03f6b55a67a9a0fa3e14f746265ad53e98a1e56a03d28d2cb90b17a01adc3dfc","abstract_canon_sha256":"98dc10c652e12b4a265bd8520c56bbe228bcfcb689b0d797cc1931e66080dda0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:57.971785Z","signature_b64":"Z0ZrO2ywpQUUnuviWopBV0yfNQIA+s02l3UV836YHb7n4KFVgIqi80DZAfO0p5bK6Qo/pzV6X8iOc2jtPV8JBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae3a1cd06880fa2b772ac885137e3a7aa4259616ca0d5a78baf98b0493255c62","last_reissued_at":"2026-07-05T03:22:57.971373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:57.971373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Vorontsova, Anton Konushin, Danila Rukhovich","submitted_at":"2021-06-02T14:20:24Z","abstract_excerpt":"In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem. To address this problem, we propose ImVoxelNet, a novel fully convolutional method of 3D object detection based on monocular or multi-view RGB images. The number of monocular images in each multi-view input can variate during training and inference; actually, this number might be unique for each multi-view input. ImVoxelNet successfully handles both indoor and outdoor scenes, which makes it general-purpose. Specifically, it achieves state-of-the-art results in car detection o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01178","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/2106.01178/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":"2106.01178","created_at":"2026-07-05T03:22:57.971437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01178v3","created_at":"2026-07-05T03:22:57.971437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01178","created_at":"2026-07-05T03:22:57.971437+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY5BZUDIQD5C","created_at":"2026-07-05T03:22:57.971437+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY5BZUDIQD5CW5ZK","created_at":"2026-07-05T03:22:57.971437+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY5BZUDI","created_at":"2026-07-05T03:22:57.971437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16229","citing_title":"TopView: Vectorising road users in a bird's eye view from uncalibrated street-level imagery with deep learning","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY5BZUDIQD5CW5ZKZCCRG7R2PK","json":"https://pith.science/pith/VY5BZUDIQD5CW5ZKZCCRG7R2PK.json","graph_json":"https://pith.science/api/pith-number/VY5BZUDIQD5CW5ZKZCCRG7R2PK/graph.json","events_json":"https://pith.science/api/pith-number/VY5BZUDIQD5CW5ZKZCCRG7R2PK/events.json","paper":"https://pith.science/paper/VY5BZUDI"},"agent_actions":{"view_html":"https://pith.science/pith/VY5BZUDIQD5CW5ZKZCCRG7R2PK","download_json":"https://pith.science/pith/VY5BZUDIQD5CW5ZKZCCRG7R2PK.json","view_paper":"https://pith.science/paper/VY5BZUDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01178&json=true","fetch_graph":"https://pith.science/api/pith-number/VY5BZUDIQD5CW5ZKZCCRG7R2PK/graph.json","fetch_events":"https://pith.science/api/pith-number/VY5BZUDIQD5CW5ZKZCCRG7R2PK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY5BZUDIQD5CW5ZKZCCRG7R2PK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY5BZUDIQD5CW5ZKZCCRG7R2PK/action/storage_attestation","attest_author":"https://pith.science/pith/VY5BZUDIQD5CW5ZKZCCRG7R2PK/action/author_attestation","sign_citation":"https://pith.science/pith/VY5BZUDIQD5CW5ZKZCCRG7R2PK/action/citation_signature","submit_replication":"https://pith.science/pith/VY5BZUDIQD5CW5ZKZCCRG7R2PK/action/replication_record"}},"created_at":"2026-07-05T03:22:57.971437+00:00","updated_at":"2026-07-05T03:22:57.971437+00:00"}