{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XGHCODE647XSPZGMESPOU5SDJ6","short_pith_number":"pith:XGHCODE6","schema_version":"1.0","canonical_sha256":"b98e270c9ee7ef27e4cc249eea76434f8aa77cb1b14ab5e01a65a233c59cf6a3","source":{"kind":"arxiv","id":"2203.15224","version":2},"attestation_state":"computed","paper":{"title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Lanyun Zhu, Shangzhan Zhang, Tianrun Chen, Xiao Fu, Xiaowei Zhou, Yichong Lu, Yiyi Liao","submitted_at":"2022-03-29T04:16:40Z","abstract_excerpt":"Large-scale training data with high-quality annotations is critical for training semantic and instance segmentation models. Unfortunately, pixel-wise annotation is labor-intensive and costly, raising the demand for more efficient labeling strategies. In this work, we present a novel 3D-to-2D label transfer method, Panoptic NeRF, which aims for obtaining per-pixel 2D semantic and instance labels from easy-to-obtain coarse 3D bounding primitives. Our method utilizes NeRF as a differentiable tool to unify coarse 3D annotations and 2D semantic cues transferred from existing datasets. We demonstrat"},"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":"2203.15224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-29T04:16:40Z","cross_cats_sorted":[],"title_canon_sha256":"6b0316abfb95785e68a86f84d5b2e82fdde9b73c5cc3579b3bfde319985606cd","abstract_canon_sha256":"043ee7120d8a3b616734ce88c8ce5e3dab0906c714516bbd3b0b579c3c9b7e14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:51.484246Z","signature_b64":"WJyn6YvH7fndHBCQdyD6i9I/RLqrDg6iNO4LP7XDq1ih35HNPxQhonAh7wsWR3J88aABOF8eXsW+RmHRgjfRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b98e270c9ee7ef27e4cc249eea76434f8aa77cb1b14ab5e01a65a233c59cf6a3","last_reissued_at":"2026-07-05T04:55:51.483781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:51.483781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Lanyun Zhu, Shangzhan Zhang, Tianrun Chen, Xiao Fu, Xiaowei Zhou, Yichong Lu, Yiyi Liao","submitted_at":"2022-03-29T04:16:40Z","abstract_excerpt":"Large-scale training data with high-quality annotations is critical for training semantic and instance segmentation models. Unfortunately, pixel-wise annotation is labor-intensive and costly, raising the demand for more efficient labeling strategies. In this work, we present a novel 3D-to-2D label transfer method, Panoptic NeRF, which aims for obtaining per-pixel 2D semantic and instance labels from easy-to-obtain coarse 3D bounding primitives. Our method utilizes NeRF as a differentiable tool to unify coarse 3D annotations and 2D semantic cues transferred from existing datasets. We demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15224","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/2203.15224/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":"2203.15224","created_at":"2026-07-05T04:55:51.483831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15224v2","created_at":"2026-07-05T04:55:51.483831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15224","created_at":"2026-07-05T04:55:51.483831+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGHCODE647XS","created_at":"2026-07-05T04:55:51.483831+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGHCODE647XSPZGM","created_at":"2026-07-05T04:55:51.483831+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGHCODE6","created_at":"2026-07-05T04:55:51.483831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2210.00379","citing_title":"NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)","ref_index":185,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGHCODE647XSPZGMESPOU5SDJ6","json":"https://pith.science/pith/XGHCODE647XSPZGMESPOU5SDJ6.json","graph_json":"https://pith.science/api/pith-number/XGHCODE647XSPZGMESPOU5SDJ6/graph.json","events_json":"https://pith.science/api/pith-number/XGHCODE647XSPZGMESPOU5SDJ6/events.json","paper":"https://pith.science/paper/XGHCODE6"},"agent_actions":{"view_html":"https://pith.science/pith/XGHCODE647XSPZGMESPOU5SDJ6","download_json":"https://pith.science/pith/XGHCODE647XSPZGMESPOU5SDJ6.json","view_paper":"https://pith.science/paper/XGHCODE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15224&json=true","fetch_graph":"https://pith.science/api/pith-number/XGHCODE647XSPZGMESPOU5SDJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/XGHCODE647XSPZGMESPOU5SDJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGHCODE647XSPZGMESPOU5SDJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGHCODE647XSPZGMESPOU5SDJ6/action/storage_attestation","attest_author":"https://pith.science/pith/XGHCODE647XSPZGMESPOU5SDJ6/action/author_attestation","sign_citation":"https://pith.science/pith/XGHCODE647XSPZGMESPOU5SDJ6/action/citation_signature","submit_replication":"https://pith.science/pith/XGHCODE647XSPZGMESPOU5SDJ6/action/replication_record"}},"created_at":"2026-07-05T04:55:51.483831+00:00","updated_at":"2026-07-05T04:55:51.483831+00:00"}