{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MBONU7P3Z72WVEVRG36VBZDAD4","short_pith_number":"pith:MBONU7P3","schema_version":"1.0","canonical_sha256":"605cda7dfbcff56a92b136fd50e4601f32fda9d30901dbb1dfcda42ed82ba6af","source":{"kind":"arxiv","id":"1811.11731","version":1},"attestation_state":"computed","paper":{"title":"CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mayank Agarwal, Navaneet K L, Priyanka Mandikal, R. Venkatesh Babu","submitted_at":"2018-11-28T18:31:46Z","abstract_excerpt":"Knowledge of 3D properties of objects is a necessity in order to build effective computer vision systems. However, lack of large scale 3D datasets can be a major constraint for data-driven approaches in learning such properties. We consider the task of single image 3D point cloud reconstruction, and aim to utilize multiple foreground masks as our supervisory data to alleviate the need for large scale 3D datasets. A novel differentiable projection module, called 'CAPNet', is introduced to obtain such 2D masks from a predicted 3D point cloud. The key idea is to model the projections as a continu"},"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":"1811.11731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-28T18:31:46Z","cross_cats_sorted":[],"title_canon_sha256":"24b7935ff122e9bab4b30500b4ccd23aa68c7e84c213dc7970a8ece7a92a9696","abstract_canon_sha256":"b3e3eb9f8eb6e7db2bbdaa643af5c4733649cabfd53ecb465c446b4d83bffb46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:40.141496Z","signature_b64":"PWwYO/ofr6DQPGuZDEHDHoYSe+Gy89Omlq6qiTHagQJRK0RL2KkLh9nSgMn7qWg8gSlmf6BwjdYQho9uTuF+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"605cda7dfbcff56a92b136fd50e4601f32fda9d30901dbb1dfcda42ed82ba6af","last_reissued_at":"2026-05-17T23:59:40.140649Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:40.140649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mayank Agarwal, Navaneet K L, Priyanka Mandikal, R. Venkatesh Babu","submitted_at":"2018-11-28T18:31:46Z","abstract_excerpt":"Knowledge of 3D properties of objects is a necessity in order to build effective computer vision systems. However, lack of large scale 3D datasets can be a major constraint for data-driven approaches in learning such properties. We consider the task of single image 3D point cloud reconstruction, and aim to utilize multiple foreground masks as our supervisory data to alleviate the need for large scale 3D datasets. A novel differentiable projection module, called 'CAPNet', is introduced to obtain such 2D masks from a predicted 3D point cloud. The key idea is to model the projections as a continu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11731","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":""},"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":"1811.11731","created_at":"2026-05-17T23:59:40.140806+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.11731v1","created_at":"2026-05-17T23:59:40.140806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11731","created_at":"2026-05-17T23:59:40.140806+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBONU7P3Z72W","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBONU7P3Z72WVEVR","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBONU7P3","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06777","citing_title":"Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBONU7P3Z72WVEVRG36VBZDAD4","json":"https://pith.science/pith/MBONU7P3Z72WVEVRG36VBZDAD4.json","graph_json":"https://pith.science/api/pith-number/MBONU7P3Z72WVEVRG36VBZDAD4/graph.json","events_json":"https://pith.science/api/pith-number/MBONU7P3Z72WVEVRG36VBZDAD4/events.json","paper":"https://pith.science/paper/MBONU7P3"},"agent_actions":{"view_html":"https://pith.science/pith/MBONU7P3Z72WVEVRG36VBZDAD4","download_json":"https://pith.science/pith/MBONU7P3Z72WVEVRG36VBZDAD4.json","view_paper":"https://pith.science/paper/MBONU7P3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.11731&json=true","fetch_graph":"https://pith.science/api/pith-number/MBONU7P3Z72WVEVRG36VBZDAD4/graph.json","fetch_events":"https://pith.science/api/pith-number/MBONU7P3Z72WVEVRG36VBZDAD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBONU7P3Z72WVEVRG36VBZDAD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBONU7P3Z72WVEVRG36VBZDAD4/action/storage_attestation","attest_author":"https://pith.science/pith/MBONU7P3Z72WVEVRG36VBZDAD4/action/author_attestation","sign_citation":"https://pith.science/pith/MBONU7P3Z72WVEVRG36VBZDAD4/action/citation_signature","submit_replication":"https://pith.science/pith/MBONU7P3Z72WVEVRG36VBZDAD4/action/replication_record"}},"created_at":"2026-05-17T23:59:40.140806+00:00","updated_at":"2026-05-17T23:59:40.140806+00:00"}