{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GGYN35A4DGZQTSOKX3EWWOKV72","short_pith_number":"pith:GGYN35A4","schema_version":"1.0","canonical_sha256":"31b0ddf41c19b309c9cabec96b3955feadb7a553118b1403db1abdc50bc565fe","source":{"kind":"arxiv","id":"2110.09482","version":3},"attestation_state":"computed","paper":{"title":"Self-Supervised Monocular Depth Estimation with Internal Feature Fusion","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Greenwood, Hang Zhou, Sarah Taylor","submitted_at":"2021-10-18T17:31:11Z","abstract_excerpt":"Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial and semantic representations from images. Therefore, it is natural to exploit semantic segmentation networks for depth estimation. In this work, based on a well-developed semantic segmentation network HRNet, we propose a novel depth estimation network DIFFNet, which can make use of semantic information in down and upsampling procedures. By applying feature "},"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":"2110.09482","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-18T17:31:11Z","cross_cats_sorted":[],"title_canon_sha256":"96ce7ba53ab06be0ddf0bfe0978a0f0af7b9ee597cf2a98428ba153e79ad4e61","abstract_canon_sha256":"9314e21bc3de4d09de9a0896e5e271237517ff7a85cec49c03581c1d9a69a4ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:23.778855Z","signature_b64":"foGbHnXF0dJqVMYCSPi4NRXJu7DC+ME7t6Ih90dw9jXuo4q2OE7BAXFsYLYDpKvyzC+b9TstxKS+Hg7MfFYMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31b0ddf41c19b309c9cabec96b3955feadb7a553118b1403db1abdc50bc565fe","last_reissued_at":"2026-07-05T03:33:23.778389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:23.778389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Monocular Depth Estimation with Internal Feature Fusion","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Greenwood, Hang Zhou, Sarah Taylor","submitted_at":"2021-10-18T17:31:11Z","abstract_excerpt":"Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial and semantic representations from images. Therefore, it is natural to exploit semantic segmentation networks for depth estimation. In this work, based on a well-developed semantic segmentation network HRNet, we propose a novel depth estimation network DIFFNet, which can make use of semantic information in down and upsampling procedures. By applying feature "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09482","kind":"arxiv","version":3},"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/2110.09482/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":"2110.09482","created_at":"2026-07-05T03:33:23.778450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.09482v3","created_at":"2026-07-05T03:33:23.778450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09482","created_at":"2026-07-05T03:33:23.778450+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGYN35A4DGZQ","created_at":"2026-07-05T03:33:23.778450+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGYN35A4DGZQTSOK","created_at":"2026-07-05T03:33:23.778450+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGYN35A4","created_at":"2026-07-05T03:33:23.778450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22686","citing_title":"SS3D: End2End Self-Supervised 3D from Web Videos","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22686","citing_title":"SS3D: End2End Self-Supervised 3D from Web Videos","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22686","citing_title":"SS3D: End2End Self-Supervised 3D from Web Videos","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGYN35A4DGZQTSOKX3EWWOKV72","json":"https://pith.science/pith/GGYN35A4DGZQTSOKX3EWWOKV72.json","graph_json":"https://pith.science/api/pith-number/GGYN35A4DGZQTSOKX3EWWOKV72/graph.json","events_json":"https://pith.science/api/pith-number/GGYN35A4DGZQTSOKX3EWWOKV72/events.json","paper":"https://pith.science/paper/GGYN35A4"},"agent_actions":{"view_html":"https://pith.science/pith/GGYN35A4DGZQTSOKX3EWWOKV72","download_json":"https://pith.science/pith/GGYN35A4DGZQTSOKX3EWWOKV72.json","view_paper":"https://pith.science/paper/GGYN35A4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.09482&json=true","fetch_graph":"https://pith.science/api/pith-number/GGYN35A4DGZQTSOKX3EWWOKV72/graph.json","fetch_events":"https://pith.science/api/pith-number/GGYN35A4DGZQTSOKX3EWWOKV72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGYN35A4DGZQTSOKX3EWWOKV72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGYN35A4DGZQTSOKX3EWWOKV72/action/storage_attestation","attest_author":"https://pith.science/pith/GGYN35A4DGZQTSOKX3EWWOKV72/action/author_attestation","sign_citation":"https://pith.science/pith/GGYN35A4DGZQTSOKX3EWWOKV72/action/citation_signature","submit_replication":"https://pith.science/pith/GGYN35A4DGZQTSOKX3EWWOKV72/action/replication_record"}},"created_at":"2026-07-05T03:33:23.778450+00:00","updated_at":"2026-07-05T03:33:23.778450+00:00"}