{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RFAFVLGR5T7H64ZWCPZEVRK66P","short_pith_number":"pith:RFAFVLGR","schema_version":"1.0","canonical_sha256":"89405aacd1ecfe7f733613f24ac55ef3d1614338182086e0466dcfa66cba55bc","source":{"kind":"arxiv","id":"1807.06009","version":1},"attestation_state":"computed","paper":{"title":"ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adarsh Kowdle, Christoph Rhemann, Julien Valentin, Michael Schoenberg, Sameh Khamis, Sean Fanello, Shahram Izadi, Thomas Funkhouser, Vladimir Tankovich, Yinda Zhang","submitted_at":"2018-07-16T16:55:19Z","abstract_excerpt":"In this paper we present ActiveStereoNet, the first deep learning solution for active stereo systems. Due to the lack of ground truth, our method is fully self-supervised, yet it produces precise depth with a subpixel precision of $1/30th$ of a pixel; it does not suffer from the common over-smoothing issues; it preserves the edges; and it explicitly handles occlusions. We introduce a novel reconstruction loss that is more robust to noise and texture-less patches, and is invariant to illumination changes. The proposed loss is optimized using a window-based cost aggregation with an adaptive supp"},"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":"1807.06009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-16T16:55:19Z","cross_cats_sorted":[],"title_canon_sha256":"70ed28a0db143260548a59f5fbecbc3216399b2a684be43cb524120acbef9ecc","abstract_canon_sha256":"b8ebc524d9f071530edb6dedaef105076eee10c4e61e90c17fb514d0c16ec907"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:36.324280Z","signature_b64":"RaiM6pTt9nB31MDGVcmv1j2a+xcwicBTJSB/RA74BDEBCe68drxyK9PT5DFXgoxXtSyTT0Gymrj+E29sqjv9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89405aacd1ecfe7f733613f24ac55ef3d1614338182086e0466dcfa66cba55bc","last_reissued_at":"2026-05-18T00:10:36.323767Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:36.323767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adarsh Kowdle, Christoph Rhemann, Julien Valentin, Michael Schoenberg, Sameh Khamis, Sean Fanello, Shahram Izadi, Thomas Funkhouser, Vladimir Tankovich, Yinda Zhang","submitted_at":"2018-07-16T16:55:19Z","abstract_excerpt":"In this paper we present ActiveStereoNet, the first deep learning solution for active stereo systems. Due to the lack of ground truth, our method is fully self-supervised, yet it produces precise depth with a subpixel precision of $1/30th$ of a pixel; it does not suffer from the common over-smoothing issues; it preserves the edges; and it explicitly handles occlusions. We introduce a novel reconstruction loss that is more robust to noise and texture-less patches, and is invariant to illumination changes. The proposed loss is optimized using a window-based cost aggregation with an adaptive supp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06009","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":"1807.06009","created_at":"2026-05-18T00:10:36.323845+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.06009v1","created_at":"2026-05-18T00:10:36.323845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06009","created_at":"2026-05-18T00:10:36.323845+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFAFVLGR5T7H","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFAFVLGR5T7H64ZW","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFAFVLGR","created_at":"2026-05-18T12:32:50.500415+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/RFAFVLGR5T7H64ZWCPZEVRK66P","json":"https://pith.science/pith/RFAFVLGR5T7H64ZWCPZEVRK66P.json","graph_json":"https://pith.science/api/pith-number/RFAFVLGR5T7H64ZWCPZEVRK66P/graph.json","events_json":"https://pith.science/api/pith-number/RFAFVLGR5T7H64ZWCPZEVRK66P/events.json","paper":"https://pith.science/paper/RFAFVLGR"},"agent_actions":{"view_html":"https://pith.science/pith/RFAFVLGR5T7H64ZWCPZEVRK66P","download_json":"https://pith.science/pith/RFAFVLGR5T7H64ZWCPZEVRK66P.json","view_paper":"https://pith.science/paper/RFAFVLGR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.06009&json=true","fetch_graph":"https://pith.science/api/pith-number/RFAFVLGR5T7H64ZWCPZEVRK66P/graph.json","fetch_events":"https://pith.science/api/pith-number/RFAFVLGR5T7H64ZWCPZEVRK66P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFAFVLGR5T7H64ZWCPZEVRK66P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFAFVLGR5T7H64ZWCPZEVRK66P/action/storage_attestation","attest_author":"https://pith.science/pith/RFAFVLGR5T7H64ZWCPZEVRK66P/action/author_attestation","sign_citation":"https://pith.science/pith/RFAFVLGR5T7H64ZWCPZEVRK66P/action/citation_signature","submit_replication":"https://pith.science/pith/RFAFVLGR5T7H64ZWCPZEVRK66P/action/replication_record"}},"created_at":"2026-05-18T00:10:36.323845+00:00","updated_at":"2026-05-18T00:10:36.323845+00:00"}