{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WHQVFGXV4PHASWPAMJ6IKU45OI","short_pith_number":"pith:WHQVFGXV","schema_version":"1.0","canonical_sha256":"b1e1529af5e3ce0959e0627c85539d722b9bffd6c678c9d9ac21d2ff65f95ec5","source":{"kind":"arxiv","id":"2604.26740","version":2},"attestation_state":"computed","paper":{"title":"Rendering-Aware Sparse Sampling for BRDF Acquisition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A sampler optimized via gradients from a fixed hypernetwork reconstructor selects sparse BRDF directions that improve low-budget material reconstruction.","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"D. J\\\"onsson, J. Unger, W. Cao, Z. Huang","submitted_at":"2026-04-29T14:39:23Z","abstract_excerpt":"Accurate BRDF acquisition is essential for realistic rendering, but dense gonioreflectometer measurements are slow and expensive. We study how to select a small set of BRDF measurements that is most informative for reconstructing material appearance under a learned BRDF prior. Existing sparse-acquisition methods often optimize samples for BRDF-space reconstruction for all materials, while the perceptual importance of a adaptive measurement ultimately depends on its effect on each rendered appearance. We therefore formulate sparse adaptive acquisition as a rendering-aware optimization problem. "},"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":"2604.26740","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-29T14:39:23Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"d87c21fe2f48afa1297f2fcfe80b1222ffe1ed4ab7793ef6061800d02ac2298d","abstract_canon_sha256":"27b10f189e8f74156eb4a574813bb14bf77426fb6e6b3f3ade87708b3dddff05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:31.346447Z","signature_b64":"R1/R6BySdVUw22j1+D08VyDevRZ7VJmD7LPFBlSUuxk4X3r2JGWqdRySWhb9cpsqoujFXVVm/SWPP4Jw1CjgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1e1529af5e3ce0959e0627c85539d722b9bffd6c678c9d9ac21d2ff65f95ec5","last_reissued_at":"2026-05-26T01:03:31.345502Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:31.345502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rendering-Aware Sparse Sampling for BRDF Acquisition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A sampler optimized via gradients from a fixed hypernetwork reconstructor selects sparse BRDF directions that improve low-budget material reconstruction.","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"D. J\\\"onsson, J. Unger, W. Cao, Z. Huang","submitted_at":"2026-04-29T14:39:23Z","abstract_excerpt":"Accurate BRDF acquisition is essential for realistic rendering, but dense gonioreflectometer measurements are slow and expensive. We study how to select a small set of BRDF measurements that is most informative for reconstructing material appearance under a learned BRDF prior. Existing sparse-acquisition methods often optimize samples for BRDF-space reconstruction for all materials, while the perceptual importance of a adaptive measurement ultimately depends on its effect on each rendered appearance. We therefore formulate sparse adaptive acquisition as a rendering-aware optimization problem. "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on the MERL dataset show that the proposed sampler improves low-budget reconstruction quality at 8 and 16 measurements compared with neural reconstruction baselines, while PCA-based methods remain strong at larger budgets.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a pretrained hypernetwork reconstructor fixed during sampler training will produce gradients that reliably identify measurement directions informative for unseen materials outside the training distribution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A sampler network learns to select informative sparse BRDF measurement directions by optimizing against a fixed pretrained hypernetwork reconstructor and differentiable renderer, improving low-budget reconstruction on the MERL dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A sampler optimized via gradients from a fixed hypernetwork reconstructor selects sparse BRDF directions that improve low-budget material reconstruction.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d9359d9d5871774f5d638ef44b3e3eafff3a370a1417cd631207c255a83bb379"},"source":{"id":"2604.26740","kind":"arxiv","version":2},"verdict":{"id":"8941f689-b9c3-4e09-9fac-6f5369585039","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T10:46:32.055379Z","strongest_claim":"Experiments on the MERL dataset show that the proposed sampler improves low-budget reconstruction quality at 8 and 16 measurements compared with neural reconstruction baselines, while PCA-based methods remain strong at larger budgets.","one_line_summary":"A sampler network learns to select informative sparse BRDF measurement directions by optimizing against a fixed pretrained hypernetwork reconstructor and differentiable renderer, improving low-budget reconstruction on the MERL dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a pretrained hypernetwork reconstructor fixed during sampler training will produce gradients that reliably identify measurement directions informative for unseen materials outside the training distribution.","pith_extraction_headline":"A sampler optimized via gradients from a fixed hypernetwork reconstructor selects sparse BRDF directions that improve low-budget material reconstruction."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.26740/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T23:42:58.501007Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T19:52:32.080953Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"5e860dad8d39b408a219c670cb0af7b1150c84e91b0cdbf8a478d565f56858e2"},"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":"2604.26740","created_at":"2026-05-26T01:03:31.345662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.26740v2","created_at":"2026-05-26T01:03:31.345662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.26740","created_at":"2026-05-26T01:03:31.345662+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHQVFGXV4PHA","created_at":"2026-05-26T01:03:31.345662+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHQVFGXV4PHASWPA","created_at":"2026-05-26T01:03:31.345662+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHQVFGXV","created_at":"2026-05-26T01:03:31.345662+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/WHQVFGXV4PHASWPAMJ6IKU45OI","json":"https://pith.science/pith/WHQVFGXV4PHASWPAMJ6IKU45OI.json","graph_json":"https://pith.science/api/pith-number/WHQVFGXV4PHASWPAMJ6IKU45OI/graph.json","events_json":"https://pith.science/api/pith-number/WHQVFGXV4PHASWPAMJ6IKU45OI/events.json","paper":"https://pith.science/paper/WHQVFGXV"},"agent_actions":{"view_html":"https://pith.science/pith/WHQVFGXV4PHASWPAMJ6IKU45OI","download_json":"https://pith.science/pith/WHQVFGXV4PHASWPAMJ6IKU45OI.json","view_paper":"https://pith.science/paper/WHQVFGXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.26740&json=true","fetch_graph":"https://pith.science/api/pith-number/WHQVFGXV4PHASWPAMJ6IKU45OI/graph.json","fetch_events":"https://pith.science/api/pith-number/WHQVFGXV4PHASWPAMJ6IKU45OI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHQVFGXV4PHASWPAMJ6IKU45OI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHQVFGXV4PHASWPAMJ6IKU45OI/action/storage_attestation","attest_author":"https://pith.science/pith/WHQVFGXV4PHASWPAMJ6IKU45OI/action/author_attestation","sign_citation":"https://pith.science/pith/WHQVFGXV4PHASWPAMJ6IKU45OI/action/citation_signature","submit_replication":"https://pith.science/pith/WHQVFGXV4PHASWPAMJ6IKU45OI/action/replication_record"}},"created_at":"2026-05-26T01:03:31.345662+00:00","updated_at":"2026-05-26T01:03:31.345662+00:00"}