{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UBZWBX7MSCUXZLJV3YURT7VT2G","short_pith_number":"pith:UBZWBX7M","schema_version":"1.0","canonical_sha256":"a07360dfec90a97cad35de2919feb3d19cfcca43434ef2b7ad36114c164dcdfc","source":{"kind":"arxiv","id":"2403.19022","version":2},"attestation_state":"computed","paper":{"title":"WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Khiem Vuong, N. Dinesh Reddy, Robert Tamburo, Srinivasa G. Narasimhan","submitted_at":"2024-03-27T21:24:20Z","abstract_excerpt":"Current methods for 2D and 3D object understanding struggle with severe occlusions in busy urban environments, partly due to the lack of large-scale labeled ground-truth annotations for learning occlusion. In this work, we introduce a novel framework for automatically generating a large, realistic dataset of dynamic objects under occlusions using freely available time-lapse imagery. By leveraging off-the-shelf 2D (bounding box, segmentation, keypoint) and 3D (pose, shape) predictions as pseudo-groundtruth, unoccluded 3D objects are identified automatically and composited into the background in"},"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":"2403.19022","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T21:24:20Z","cross_cats_sorted":[],"title_canon_sha256":"aac8a06b8a8f31a49972a1172385b0c7ae33533223477a442f84233820abe4ae","abstract_canon_sha256":"33699b3f1d2650ed6d8700d6a00fa9587bf5f92e38778a4c972c2038d271031e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:11.802244Z","signature_b64":"1pdDFSSigbUj/dm4fCJcGuokJQWz2yQ+JJEGjJmAmEeAp0JWB2+iYI3Hsecf+zb4tGGaz+X7eh0C7QTEydYqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a07360dfec90a97cad35de2919feb3d19cfcca43434ef2b7ad36114c164dcdfc","last_reissued_at":"2026-07-05T08:03:11.801746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:11.801746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Khiem Vuong, N. Dinesh Reddy, Robert Tamburo, Srinivasa G. Narasimhan","submitted_at":"2024-03-27T21:24:20Z","abstract_excerpt":"Current methods for 2D and 3D object understanding struggle with severe occlusions in busy urban environments, partly due to the lack of large-scale labeled ground-truth annotations for learning occlusion. In this work, we introduce a novel framework for automatically generating a large, realistic dataset of dynamic objects under occlusions using freely available time-lapse imagery. By leveraging off-the-shelf 2D (bounding box, segmentation, keypoint) and 3D (pose, shape) predictions as pseudo-groundtruth, unoccluded 3D objects are identified automatically and composited into the background in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19022","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/2403.19022/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":"2403.19022","created_at":"2026-07-05T08:03:11.801804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19022v2","created_at":"2026-07-05T08:03:11.801804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19022","created_at":"2026-07-05T08:03:11.801804+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBZWBX7MSCUX","created_at":"2026-07-05T08:03:11.801804+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBZWBX7MSCUXZLJV","created_at":"2026-07-05T08:03:11.801804+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBZWBX7M","created_at":"2026-07-05T08:03:11.801804+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBZWBX7MSCUXZLJV3YURT7VT2G","json":"https://pith.science/pith/UBZWBX7MSCUXZLJV3YURT7VT2G.json","graph_json":"https://pith.science/api/pith-number/UBZWBX7MSCUXZLJV3YURT7VT2G/graph.json","events_json":"https://pith.science/api/pith-number/UBZWBX7MSCUXZLJV3YURT7VT2G/events.json","paper":"https://pith.science/paper/UBZWBX7M"},"agent_actions":{"view_html":"https://pith.science/pith/UBZWBX7MSCUXZLJV3YURT7VT2G","download_json":"https://pith.science/pith/UBZWBX7MSCUXZLJV3YURT7VT2G.json","view_paper":"https://pith.science/paper/UBZWBX7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19022&json=true","fetch_graph":"https://pith.science/api/pith-number/UBZWBX7MSCUXZLJV3YURT7VT2G/graph.json","fetch_events":"https://pith.science/api/pith-number/UBZWBX7MSCUXZLJV3YURT7VT2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBZWBX7MSCUXZLJV3YURT7VT2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBZWBX7MSCUXZLJV3YURT7VT2G/action/storage_attestation","attest_author":"https://pith.science/pith/UBZWBX7MSCUXZLJV3YURT7VT2G/action/author_attestation","sign_citation":"https://pith.science/pith/UBZWBX7MSCUXZLJV3YURT7VT2G/action/citation_signature","submit_replication":"https://pith.science/pith/UBZWBX7MSCUXZLJV3YURT7VT2G/action/replication_record"}},"created_at":"2026-07-05T08:03:11.801804+00:00","updated_at":"2026-07-05T08:03:11.801804+00:00"}