{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BNPVC6TT4Y5EVDK2ONMLRRJOG2","short_pith_number":"pith:BNPVC6TT","schema_version":"1.0","canonical_sha256":"0b5f517a73e63a4a8d5a7358b8c52e369a23adfcc1d374da3c9900ec210c163a","source":{"kind":"arxiv","id":"2512.09925","version":2},"attestation_state":"computed","paper":{"title":"GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Didier Stricker, Jun Myeong Choi, Patrick Noras, Pieter Peers, Roni Sengupta","submitted_at":"2025-12-10T18:58:11Z","abstract_excerpt":"Recent advances in Gaussian Splatting-based inverse rendering extend Gaussian primitives with shading parameters and physically grounded light transport, enabling high-quality material recovery from dense multi-view captures. However, the accuracy of these methods degrades under sparse-view settings, where limited observations lead to severe ambiguity between geometry, reflectance, and lighting. We introduce GAINS (Gaussian-based Inverse rendering from Sparse multi-view captures), a two-stage inverse rendering framework that leverages foundation models as priors to stabilize geometry and mater"},"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":"2512.09925","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-10T18:58:11Z","cross_cats_sorted":[],"title_canon_sha256":"c2641c0bf36b9d8e4098e4796ee0e8b031bc77603ad0bd50b548acc3a9135a44","abstract_canon_sha256":"0880c05af30356b0eae8f7c25ad4e4eff798d89a918f753cc3b75e636e3f8951"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:21:48.537719Z","signature_b64":"VSdCPt33JVrWGZpBsN5NBXvjLsyoiPILxaAVgU3Q+cj1gqs2aAqwTUNZ/639dDDVF7dVq4JHY97d5chlwyzGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b5f517a73e63a4a8d5a7358b8c52e369a23adfcc1d374da3c9900ec210c163a","last_reissued_at":"2026-07-15T01:21:48.536809Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:21:48.536809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Didier Stricker, Jun Myeong Choi, Patrick Noras, Pieter Peers, Roni Sengupta","submitted_at":"2025-12-10T18:58:11Z","abstract_excerpt":"Recent advances in Gaussian Splatting-based inverse rendering extend Gaussian primitives with shading parameters and physically grounded light transport, enabling high-quality material recovery from dense multi-view captures. However, the accuracy of these methods degrades under sparse-view settings, where limited observations lead to severe ambiguity between geometry, reflectance, and lighting. We introduce GAINS (Gaussian-based Inverse rendering from Sparse multi-view captures), a two-stage inverse rendering framework that leverages foundation models as priors to stabilize geometry and mater"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.09925","kind":"arxiv","version":2},"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/2512.09925/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":"2512.09925","created_at":"2026-07-15T01:21:48.537237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.09925v2","created_at":"2026-07-15T01:21:48.537237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.09925","created_at":"2026-07-15T01:21:48.537237+00:00"},{"alias_kind":"pith_short_12","alias_value":"BNPVC6TT4Y5E","created_at":"2026-07-15T01:21:48.537237+00:00"},{"alias_kind":"pith_short_16","alias_value":"BNPVC6TT4Y5EVDK2","created_at":"2026-07-15T01:21:48.537237+00:00"},{"alias_kind":"pith_short_8","alias_value":"BNPVC6TT","created_at":"2026-07-15T01:21:48.537237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.11314","citing_title":"TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructions","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BNPVC6TT4Y5EVDK2ONMLRRJOG2","json":"https://pith.science/pith/BNPVC6TT4Y5EVDK2ONMLRRJOG2.json","graph_json":"https://pith.science/api/pith-number/BNPVC6TT4Y5EVDK2ONMLRRJOG2/graph.json","events_json":"https://pith.science/api/pith-number/BNPVC6TT4Y5EVDK2ONMLRRJOG2/events.json","paper":"https://pith.science/paper/BNPVC6TT"},"agent_actions":{"view_html":"https://pith.science/pith/BNPVC6TT4Y5EVDK2ONMLRRJOG2","download_json":"https://pith.science/pith/BNPVC6TT4Y5EVDK2ONMLRRJOG2.json","view_paper":"https://pith.science/paper/BNPVC6TT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.09925&json=true","fetch_graph":"https://pith.science/api/pith-number/BNPVC6TT4Y5EVDK2ONMLRRJOG2/graph.json","fetch_events":"https://pith.science/api/pith-number/BNPVC6TT4Y5EVDK2ONMLRRJOG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BNPVC6TT4Y5EVDK2ONMLRRJOG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BNPVC6TT4Y5EVDK2ONMLRRJOG2/action/storage_attestation","attest_author":"https://pith.science/pith/BNPVC6TT4Y5EVDK2ONMLRRJOG2/action/author_attestation","sign_citation":"https://pith.science/pith/BNPVC6TT4Y5EVDK2ONMLRRJOG2/action/citation_signature","submit_replication":"https://pith.science/pith/BNPVC6TT4Y5EVDK2ONMLRRJOG2/action/replication_record"}},"created_at":"2026-07-15T01:21:48.537237+00:00","updated_at":"2026-07-15T01:21:48.537237+00:00"}