{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UOT5ZQ5R5JWUEXI6XDXGDI3HBV","short_pith_number":"pith:UOT5ZQ5R","schema_version":"1.0","canonical_sha256":"a3a7dcc3b1ea6d425d1eb8ee61a3670d62cfc0c5fc7d1bd5891afc772c87bad9","source":{"kind":"arxiv","id":"1911.09204","version":4},"attestation_state":"computed","paper":{"title":"DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Akshay Gadi Patil, Hao Zhang, Jiongchao Jin, Zhang Xiong","submitted_at":"2019-11-20T22:57:51Z","abstract_excerpt":"We introduce a differential visual similarity metric to train deep neural networks for 3D reconstruction, aimed at improving reconstruction quality. The metric compares two 3D shapes by measuring distances between multi-view images differentiably rendered from the shapes. Importantly, the image-space distance is also differentiable and measures visual similarity, rather than pixel-wise distortion. Specifically, the similarity is defined by mean-squared errors over HardNet features computed from probabilistic keypoint maps of the compared images. Our differential visual shape similarity metric "},"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":"1911.09204","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2019-11-20T22:57:51Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c9a7291b9d75c0310111a94e69238a5b07271510e8c470c9700145c48a819801","abstract_canon_sha256":"c58e413721de55b9326f2a965e004240dd081494f1c6e93f9d19adc78f48f0f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:53.482500Z","signature_b64":"NmnWPW7mGdL89gKOiUjP4TMhjJSNFKwvSYWkJdzVIO5zJnClSfnH8kdEfuLxY/JyITp5esaPnqYOUpEeY29uAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a7dcc3b1ea6d425d1eb8ee61a3670d62cfc0c5fc7d1bd5891afc772c87bad9","last_reissued_at":"2026-07-05T00:51:53.482066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:53.482066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Akshay Gadi Patil, Hao Zhang, Jiongchao Jin, Zhang Xiong","submitted_at":"2019-11-20T22:57:51Z","abstract_excerpt":"We introduce a differential visual similarity metric to train deep neural networks for 3D reconstruction, aimed at improving reconstruction quality. The metric compares two 3D shapes by measuring distances between multi-view images differentiably rendered from the shapes. Importantly, the image-space distance is also differentiable and measures visual similarity, rather than pixel-wise distortion. Specifically, the similarity is defined by mean-squared errors over HardNet features computed from probabilistic keypoint maps of the compared images. Our differential visual shape similarity metric "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09204","kind":"arxiv","version":4},"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/1911.09204/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":"1911.09204","created_at":"2026-07-05T00:51:53.482122+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.09204v4","created_at":"2026-07-05T00:51:53.482122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09204","created_at":"2026-07-05T00:51:53.482122+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOT5ZQ5R5JWU","created_at":"2026-07-05T00:51:53.482122+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOT5ZQ5R5JWUEXI6","created_at":"2026-07-05T00:51:53.482122+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOT5ZQ5R","created_at":"2026-07-05T00:51:53.482122+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/UOT5ZQ5R5JWUEXI6XDXGDI3HBV","json":"https://pith.science/pith/UOT5ZQ5R5JWUEXI6XDXGDI3HBV.json","graph_json":"https://pith.science/api/pith-number/UOT5ZQ5R5JWUEXI6XDXGDI3HBV/graph.json","events_json":"https://pith.science/api/pith-number/UOT5ZQ5R5JWUEXI6XDXGDI3HBV/events.json","paper":"https://pith.science/paper/UOT5ZQ5R"},"agent_actions":{"view_html":"https://pith.science/pith/UOT5ZQ5R5JWUEXI6XDXGDI3HBV","download_json":"https://pith.science/pith/UOT5ZQ5R5JWUEXI6XDXGDI3HBV.json","view_paper":"https://pith.science/paper/UOT5ZQ5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.09204&json=true","fetch_graph":"https://pith.science/api/pith-number/UOT5ZQ5R5JWUEXI6XDXGDI3HBV/graph.json","fetch_events":"https://pith.science/api/pith-number/UOT5ZQ5R5JWUEXI6XDXGDI3HBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOT5ZQ5R5JWUEXI6XDXGDI3HBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOT5ZQ5R5JWUEXI6XDXGDI3HBV/action/storage_attestation","attest_author":"https://pith.science/pith/UOT5ZQ5R5JWUEXI6XDXGDI3HBV/action/author_attestation","sign_citation":"https://pith.science/pith/UOT5ZQ5R5JWUEXI6XDXGDI3HBV/action/citation_signature","submit_replication":"https://pith.science/pith/UOT5ZQ5R5JWUEXI6XDXGDI3HBV/action/replication_record"}},"created_at":"2026-07-05T00:51:53.482122+00:00","updated_at":"2026-07-05T00:51:53.482122+00:00"}