{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZWJKIBNLI6P3T4W3Y4YNL7RMNB","short_pith_number":"pith:ZWJKIBNL","schema_version":"1.0","canonical_sha256":"cd92a405ab479fb9f2dbc730d5fe2c6871258b074d2d1311dd2c57e9aa5cfb38","source":{"kind":"arxiv","id":"2605.25426","version":1},"attestation_state":"computed","paper":{"title":"Learning View-Dependent Splatting Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Fan Pei, Hongzhi Wu, Huakeng Ding, Kun Zhou, Zhanpeng Liu","submitted_at":"2026-05-25T04:57:25Z","abstract_excerpt":"We present a differentiable framework to automatically learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency for novel 3D view synthesis. Our volumetric primitive is defined as a bounding ellipsoid and a 3D-kernel latent vector. We first learn a projection network to output a 2D-kernel latent, taking the attributes of the ellipsoid and the 3D-kernel latent as input. Next, the result is sent to a decoder to produce a radially symmetric 2D kernel in terms of Mahalanobis distance, bounded by the projected ellipsoid. The neura"},"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":"2605.25426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-05-25T04:57:25Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2c51b53c3324d194d86f91199e0fb04fbbd8506310bad90b7eed4b815397772e","abstract_canon_sha256":"9eadd8742fda95093200f0ca6566353c5a9f1a06b82dfa44485a4f979f32cf81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:34.425813Z","signature_b64":"zR7Zix5slJcu2lenZpwIepvxb4YeohyCS+3F6t98lFBeHd9laSj4TC7rSz9zAGedFBJl/FiaHQklMrk8lDK5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd92a405ab479fb9f2dbc730d5fe2c6871258b074d2d1311dd2c57e9aa5cfb38","last_reissued_at":"2026-05-26T02:04:34.424973Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:34.424973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning View-Dependent Splatting Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Fan Pei, Hongzhi Wu, Huakeng Ding, Kun Zhou, Zhanpeng Liu","submitted_at":"2026-05-25T04:57:25Z","abstract_excerpt":"We present a differentiable framework to automatically learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency for novel 3D view synthesis. Our volumetric primitive is defined as a bounding ellipsoid and a 3D-kernel latent vector. We first learn a projection network to output a 2D-kernel latent, taking the attributes of the ellipsoid and the 3D-kernel latent as input. Next, the result is sent to a decoder to produce a radially symmetric 2D kernel in terms of Mahalanobis distance, bounded by the projected ellipsoid. The neura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25426","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/2605.25426/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":"2605.25426","created_at":"2026-05-26T02:04:34.425116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25426v1","created_at":"2026-05-26T02:04:34.425116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25426","created_at":"2026-05-26T02:04:34.425116+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWJKIBNLI6P3","created_at":"2026-05-26T02:04:34.425116+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWJKIBNLI6P3T4W3","created_at":"2026-05-26T02:04:34.425116+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWJKIBNL","created_at":"2026-05-26T02:04:34.425116+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/ZWJKIBNLI6P3T4W3Y4YNL7RMNB","json":"https://pith.science/pith/ZWJKIBNLI6P3T4W3Y4YNL7RMNB.json","graph_json":"https://pith.science/api/pith-number/ZWJKIBNLI6P3T4W3Y4YNL7RMNB/graph.json","events_json":"https://pith.science/api/pith-number/ZWJKIBNLI6P3T4W3Y4YNL7RMNB/events.json","paper":"https://pith.science/paper/ZWJKIBNL"},"agent_actions":{"view_html":"https://pith.science/pith/ZWJKIBNLI6P3T4W3Y4YNL7RMNB","download_json":"https://pith.science/pith/ZWJKIBNLI6P3T4W3Y4YNL7RMNB.json","view_paper":"https://pith.science/paper/ZWJKIBNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25426&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWJKIBNLI6P3T4W3Y4YNL7RMNB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWJKIBNLI6P3T4W3Y4YNL7RMNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWJKIBNLI6P3T4W3Y4YNL7RMNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWJKIBNLI6P3T4W3Y4YNL7RMNB/action/storage_attestation","attest_author":"https://pith.science/pith/ZWJKIBNLI6P3T4W3Y4YNL7RMNB/action/author_attestation","sign_citation":"https://pith.science/pith/ZWJKIBNLI6P3T4W3Y4YNL7RMNB/action/citation_signature","submit_replication":"https://pith.science/pith/ZWJKIBNLI6P3T4W3Y4YNL7RMNB/action/replication_record"}},"created_at":"2026-05-26T02:04:34.425116+00:00","updated_at":"2026-05-26T02:04:34.425116+00:00"}