{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IZ7VTY3PKFKK2DRKDLC72Z3LJ3","short_pith_number":"pith:IZ7VTY3P","schema_version":"1.0","canonical_sha256":"467f59e36f5154ad0e2a1ac5fd676b4ee51460702f17803deb6ee4f3be2cea87","source":{"kind":"arxiv","id":"2406.10722","version":1},"attestation_state":"computed","paper":{"title":"GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ambrish Tyagi, Ashish Shrivastava, Avinash Ravichandran, Bharat Singh, Luyu Yang, Viveka Kulharia","submitted_at":"2024-06-15T19:29:01Z","abstract_excerpt":"Multimodal synthetic data generation is crucial in domains such as autonomous driving, robotics, augmented/virtual reality, and retail. We propose a novel approach, GenMM, for jointly editing RGB videos and LiDAR scans by inserting temporally and geometrically consistent 3D objects. Our method uses a reference image and 3D bounding boxes to seamlessly insert and blend new objects into target videos. We inpaint the 2D Regions of Interest (consistent with 3D boxes) using a diffusion-based video inpainting model. We then compute semantic boundaries of the object and estimate it's surface depth us"},"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":"2406.10722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-15T19:29:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"729bdd03f14faa3a8694fd23e31f7a63e498681b8ab852d07e428d903384ce11","abstract_canon_sha256":"3db06c67d6f2130b0481740fb3fcb521022f42b1ddfdd2823544c9f56e76e1aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:20.947752Z","signature_b64":"MDAvQsPGRNtE/s9OTV4pWImJr5uyuQw3K4UbkTYULJLRQfJfl3K7SacdCnvzu7eMUgOVew2IPoJSrYi9sL6MAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"467f59e36f5154ad0e2a1ac5fd676b4ee51460702f17803deb6ee4f3be2cea87","last_reissued_at":"2026-07-05T08:32:20.947268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:20.947268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ambrish Tyagi, Ashish Shrivastava, Avinash Ravichandran, Bharat Singh, Luyu Yang, Viveka Kulharia","submitted_at":"2024-06-15T19:29:01Z","abstract_excerpt":"Multimodal synthetic data generation is crucial in domains such as autonomous driving, robotics, augmented/virtual reality, and retail. We propose a novel approach, GenMM, for jointly editing RGB videos and LiDAR scans by inserting temporally and geometrically consistent 3D objects. Our method uses a reference image and 3D bounding boxes to seamlessly insert and blend new objects into target videos. We inpaint the 2D Regions of Interest (consistent with 3D boxes) using a diffusion-based video inpainting model. We then compute semantic boundaries of the object and estimate it's surface depth us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10722","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/2406.10722/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":"2406.10722","created_at":"2026-07-05T08:32:20.947328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10722v1","created_at":"2026-07-05T08:32:20.947328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10722","created_at":"2026-07-05T08:32:20.947328+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZ7VTY3PKFKK","created_at":"2026-07-05T08:32:20.947328+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZ7VTY3PKFKK2DRK","created_at":"2026-07-05T08:32:20.947328+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZ7VTY3P","created_at":"2026-07-05T08:32:20.947328+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22809","citing_title":"Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22809","citing_title":"Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IZ7VTY3PKFKK2DRKDLC72Z3LJ3","json":"https://pith.science/pith/IZ7VTY3PKFKK2DRKDLC72Z3LJ3.json","graph_json":"https://pith.science/api/pith-number/IZ7VTY3PKFKK2DRKDLC72Z3LJ3/graph.json","events_json":"https://pith.science/api/pith-number/IZ7VTY3PKFKK2DRKDLC72Z3LJ3/events.json","paper":"https://pith.science/paper/IZ7VTY3P"},"agent_actions":{"view_html":"https://pith.science/pith/IZ7VTY3PKFKK2DRKDLC72Z3LJ3","download_json":"https://pith.science/pith/IZ7VTY3PKFKK2DRKDLC72Z3LJ3.json","view_paper":"https://pith.science/paper/IZ7VTY3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10722&json=true","fetch_graph":"https://pith.science/api/pith-number/IZ7VTY3PKFKK2DRKDLC72Z3LJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/IZ7VTY3PKFKK2DRKDLC72Z3LJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZ7VTY3PKFKK2DRKDLC72Z3LJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZ7VTY3PKFKK2DRKDLC72Z3LJ3/action/storage_attestation","attest_author":"https://pith.science/pith/IZ7VTY3PKFKK2DRKDLC72Z3LJ3/action/author_attestation","sign_citation":"https://pith.science/pith/IZ7VTY3PKFKK2DRKDLC72Z3LJ3/action/citation_signature","submit_replication":"https://pith.science/pith/IZ7VTY3PKFKK2DRKDLC72Z3LJ3/action/replication_record"}},"created_at":"2026-07-05T08:32:20.947328+00:00","updated_at":"2026-07-05T08:32:20.947328+00:00"}