{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7XHGI3BVGP3XZ74HJ7E4ZBTNTK","short_pith_number":"pith:7XHGI3BV","schema_version":"1.0","canonical_sha256":"fdce646c3533f77cff874fc9cc866d9ab1e2d083510bf258c1510bba1943ec56","source":{"kind":"arxiv","id":"1804.05195","version":2},"attestation_state":"computed","paper":{"title":"Motion-based Object Segmentation based on Dense RGB-D Scene Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jeannette Bohg, Lin Shao, Parth Shah, Vikranth Dwaracherla","submitted_at":"2018-04-14T09:33:40Z","abstract_excerpt":"Given two consecutive RGB-D images, we propose a model that estimates a dense 3D motion field, also known as scene flow. We take advantage of the fact that in robot manipulation scenarios, scenes often consist of a set of rigidly moving objects. Our model jointly estimates (i) the segmentation of the scene into an unknown but finite number of objects, (ii) the motion trajectories of these objects and (iii) the object scene flow. We employ an hourglass, deep neural network architecture. In the encoding stage, the RGB and depth images undergo spatial compression and correlation. In the decoding "},"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":"1804.05195","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-04-14T09:33:40Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"dd632978399349f89fe24c5d1f83b041abf74f8b73a2d39950199f279dc6e99d","abstract_canon_sha256":"538148ebe4e0c56b051f16da23967686738a5b00a21984da4aedf82c09ed9ed5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:01.914026Z","signature_b64":"B957Q/6nv4RAqkdc1NcN0/Mmeg1IWJ/INlvzEq4Jf0XeVgtcqqSfBWll0pB/AFg+3uHNnNKKaQjc14xQtjygAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdce646c3533f77cff874fc9cc866d9ab1e2d083510bf258c1510bba1943ec56","last_reissued_at":"2026-05-18T00:10:01.913279Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:01.913279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motion-based Object Segmentation based on Dense RGB-D Scene Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jeannette Bohg, Lin Shao, Parth Shah, Vikranth Dwaracherla","submitted_at":"2018-04-14T09:33:40Z","abstract_excerpt":"Given two consecutive RGB-D images, we propose a model that estimates a dense 3D motion field, also known as scene flow. We take advantage of the fact that in robot manipulation scenarios, scenes often consist of a set of rigidly moving objects. Our model jointly estimates (i) the segmentation of the scene into an unknown but finite number of objects, (ii) the motion trajectories of these objects and (iii) the object scene flow. We employ an hourglass, deep neural network architecture. In the encoding stage, the RGB and depth images undergo spatial compression and correlation. In the decoding "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05195","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":""},"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":"1804.05195","created_at":"2026-05-18T00:10:01.913414+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.05195v2","created_at":"2026-05-18T00:10:01.913414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05195","created_at":"2026-05-18T00:10:01.913414+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XHGI3BVGP3X","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XHGI3BVGP3XZ74H","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XHGI3BV","created_at":"2026-05-18T12:32:11.075285+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/7XHGI3BVGP3XZ74HJ7E4ZBTNTK","json":"https://pith.science/pith/7XHGI3BVGP3XZ74HJ7E4ZBTNTK.json","graph_json":"https://pith.science/api/pith-number/7XHGI3BVGP3XZ74HJ7E4ZBTNTK/graph.json","events_json":"https://pith.science/api/pith-number/7XHGI3BVGP3XZ74HJ7E4ZBTNTK/events.json","paper":"https://pith.science/paper/7XHGI3BV"},"agent_actions":{"view_html":"https://pith.science/pith/7XHGI3BVGP3XZ74HJ7E4ZBTNTK","download_json":"https://pith.science/pith/7XHGI3BVGP3XZ74HJ7E4ZBTNTK.json","view_paper":"https://pith.science/paper/7XHGI3BV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.05195&json=true","fetch_graph":"https://pith.science/api/pith-number/7XHGI3BVGP3XZ74HJ7E4ZBTNTK/graph.json","fetch_events":"https://pith.science/api/pith-number/7XHGI3BVGP3XZ74HJ7E4ZBTNTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XHGI3BVGP3XZ74HJ7E4ZBTNTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XHGI3BVGP3XZ74HJ7E4ZBTNTK/action/storage_attestation","attest_author":"https://pith.science/pith/7XHGI3BVGP3XZ74HJ7E4ZBTNTK/action/author_attestation","sign_citation":"https://pith.science/pith/7XHGI3BVGP3XZ74HJ7E4ZBTNTK/action/citation_signature","submit_replication":"https://pith.science/pith/7XHGI3BVGP3XZ74HJ7E4ZBTNTK/action/replication_record"}},"created_at":"2026-05-18T00:10:01.913414+00:00","updated_at":"2026-05-18T00:10:01.913414+00:00"}