{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:B7E4TZNEUKICQDHGRWAFX4IT42","short_pith_number":"pith:B7E4TZNE","schema_version":"1.0","canonical_sha256":"0fc9c9e5a4a290280ce68d805bf113e68bcdaaf8c9e800c5137b91f5d407aeec","source":{"kind":"arxiv","id":"1710.07368","version":1},"attestation_state":"computed","paper":{"title":"SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alvin Wan, Bichen Wu, Kurt Keutzer, Xiangyu Yue","submitted_at":"2017-10-19T23:03:33Z","abstract_excerpt":"In this paper, we address semantic segmentation of road-objects from 3D LiDAR point clouds. In particular, we wish to detect and categorize instances of interest, such as cars, pedestrians and cyclists. We formulate this problem as a point- wise classification problem, and propose an end-to-end pipeline called SqueezeSeg based on convolutional neural networks (CNN): the CNN takes a transformed LiDAR point cloud as input and directly outputs a point-wise label map, which is then refined by a conditional random field (CRF) implemented as a recurrent layer. Instance-level labels are then obtained"},"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":"1710.07368","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-19T23:03:33Z","cross_cats_sorted":[],"title_canon_sha256":"24f71245601e7ed97313435f2ece2e7ea3f80e55c3355fe4d543baf77f5e5d88","abstract_canon_sha256":"a48039503ef6f2c7455d3105eb689bec9ad2dcb441c7fc4ca60d1b443c591bcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:25.035791Z","signature_b64":"E0UIR9HgjTxt1TOOKJOXtOKG6/032xalq5dP7A2lPTe6n8Fk3c8bYeBCFzx+i0wf/9lXj6f1XJKj3AdMYXeHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fc9c9e5a4a290280ce68d805bf113e68bcdaaf8c9e800c5137b91f5d407aeec","last_reissued_at":"2026-05-18T00:32:25.035198Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:25.035198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alvin Wan, Bichen Wu, Kurt Keutzer, Xiangyu Yue","submitted_at":"2017-10-19T23:03:33Z","abstract_excerpt":"In this paper, we address semantic segmentation of road-objects from 3D LiDAR point clouds. In particular, we wish to detect and categorize instances of interest, such as cars, pedestrians and cyclists. We formulate this problem as a point- wise classification problem, and propose an end-to-end pipeline called SqueezeSeg based on convolutional neural networks (CNN): the CNN takes a transformed LiDAR point cloud as input and directly outputs a point-wise label map, which is then refined by a conditional random field (CRF) implemented as a recurrent layer. Instance-level labels are then obtained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07368","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":"1710.07368","created_at":"2026-05-18T00:32:25.035269+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.07368v1","created_at":"2026-05-18T00:32:25.035269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07368","created_at":"2026-05-18T00:32:25.035269+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7E4TZNEUKIC","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7E4TZNEUKICQDHG","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7E4TZNE","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.04758","citing_title":"SynthCity: A large scale synthetic point cloud","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07061","citing_title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02098","citing_title":"From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02098","citing_title":"From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7E4TZNEUKICQDHGRWAFX4IT42","json":"https://pith.science/pith/B7E4TZNEUKICQDHGRWAFX4IT42.json","graph_json":"https://pith.science/api/pith-number/B7E4TZNEUKICQDHGRWAFX4IT42/graph.json","events_json":"https://pith.science/api/pith-number/B7E4TZNEUKICQDHGRWAFX4IT42/events.json","paper":"https://pith.science/paper/B7E4TZNE"},"agent_actions":{"view_html":"https://pith.science/pith/B7E4TZNEUKICQDHGRWAFX4IT42","download_json":"https://pith.science/pith/B7E4TZNEUKICQDHGRWAFX4IT42.json","view_paper":"https://pith.science/paper/B7E4TZNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.07368&json=true","fetch_graph":"https://pith.science/api/pith-number/B7E4TZNEUKICQDHGRWAFX4IT42/graph.json","fetch_events":"https://pith.science/api/pith-number/B7E4TZNEUKICQDHGRWAFX4IT42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7E4TZNEUKICQDHGRWAFX4IT42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7E4TZNEUKICQDHGRWAFX4IT42/action/storage_attestation","attest_author":"https://pith.science/pith/B7E4TZNEUKICQDHGRWAFX4IT42/action/author_attestation","sign_citation":"https://pith.science/pith/B7E4TZNEUKICQDHGRWAFX4IT42/action/citation_signature","submit_replication":"https://pith.science/pith/B7E4TZNEUKICQDHGRWAFX4IT42/action/replication_record"}},"created_at":"2026-05-18T00:32:25.035269+00:00","updated_at":"2026-05-18T00:32:25.035269+00:00"}