{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P4IBKWZZ2AWUET3JPDNXBUYQJQ","short_pith_number":"pith:P4IBKWZZ","schema_version":"1.0","canonical_sha256":"7f10155b39d02d424f6978db70d3104c2a529fcc1b36c59d9298c09043246b5c","source":{"kind":"arxiv","id":"2404.05181","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Learning for Multi-view Stereo Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Min, Jie Zhao, Qinglu Min, Zhihao Zhang","submitted_at":"2024-04-08T04:13:35Z","abstract_excerpt":"Deep learning has recently demonstrated its excellent performance on the task of multi-view stereo (MVS). However, loss functions applied for deep MVS are rarely studied. In this paper, we first analyze existing loss functions' properties for deep depth based MVS approaches. Regression based loss leads to inaccurate continuous results by computing mathematical expectation, while classification based loss outputs discretized depth values. To this end, we then propose a novel loss function, named adaptive Wasserstein loss, which is able to narrow down the difference between the true and predicte"},"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":"2404.05181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T04:13:35Z","cross_cats_sorted":[],"title_canon_sha256":"17afbadcfc5bd4fabf925a66abc8b90f644a0d5ab95bac8d70f2602f65532917","abstract_canon_sha256":"de9902f197b3a18ab5b05ef6392ae08cc0875eab6000bd94dc3c7dc8467f363b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:27.222656Z","signature_b64":"CZmI6vA7aoqEuDBa0TCjkzc9UQ8/nv6o30nec8ZzTCyw3jxfNtjZSUiDlXRGUOXm9yYv6GFwED5JlsW0llTUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f10155b39d02d424f6978db70d3104c2a529fcc1b36c59d9298c09043246b5c","last_reissued_at":"2026-07-05T08:05:27.222186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:27.222186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Learning for Multi-view Stereo Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Min, Jie Zhao, Qinglu Min, Zhihao Zhang","submitted_at":"2024-04-08T04:13:35Z","abstract_excerpt":"Deep learning has recently demonstrated its excellent performance on the task of multi-view stereo (MVS). However, loss functions applied for deep MVS are rarely studied. In this paper, we first analyze existing loss functions' properties for deep depth based MVS approaches. Regression based loss leads to inaccurate continuous results by computing mathematical expectation, while classification based loss outputs discretized depth values. To this end, we then propose a novel loss function, named adaptive Wasserstein loss, which is able to narrow down the difference between the true and predicte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05181","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.05181/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":"2404.05181","created_at":"2026-07-05T08:05:27.222250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05181v1","created_at":"2026-07-05T08:05:27.222250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05181","created_at":"2026-07-05T08:05:27.222250+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4IBKWZZ2AWU","created_at":"2026-07-05T08:05:27.222250+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4IBKWZZ2AWUET3J","created_at":"2026-07-05T08:05:27.222250+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4IBKWZZ","created_at":"2026-07-05T08:05:27.222250+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/P4IBKWZZ2AWUET3JPDNXBUYQJQ","json":"https://pith.science/pith/P4IBKWZZ2AWUET3JPDNXBUYQJQ.json","graph_json":"https://pith.science/api/pith-number/P4IBKWZZ2AWUET3JPDNXBUYQJQ/graph.json","events_json":"https://pith.science/api/pith-number/P4IBKWZZ2AWUET3JPDNXBUYQJQ/events.json","paper":"https://pith.science/paper/P4IBKWZZ"},"agent_actions":{"view_html":"https://pith.science/pith/P4IBKWZZ2AWUET3JPDNXBUYQJQ","download_json":"https://pith.science/pith/P4IBKWZZ2AWUET3JPDNXBUYQJQ.json","view_paper":"https://pith.science/paper/P4IBKWZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05181&json=true","fetch_graph":"https://pith.science/api/pith-number/P4IBKWZZ2AWUET3JPDNXBUYQJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/P4IBKWZZ2AWUET3JPDNXBUYQJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4IBKWZZ2AWUET3JPDNXBUYQJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4IBKWZZ2AWUET3JPDNXBUYQJQ/action/storage_attestation","attest_author":"https://pith.science/pith/P4IBKWZZ2AWUET3JPDNXBUYQJQ/action/author_attestation","sign_citation":"https://pith.science/pith/P4IBKWZZ2AWUET3JPDNXBUYQJQ/action/citation_signature","submit_replication":"https://pith.science/pith/P4IBKWZZ2AWUET3JPDNXBUYQJQ/action/replication_record"}},"created_at":"2026-07-05T08:05:27.222250+00:00","updated_at":"2026-07-05T08:05:27.222250+00:00"}