{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A27AWBTZBD3IFUTA4O42AVWIX4","short_pith_number":"pith:A27AWBTZ","schema_version":"1.0","canonical_sha256":"06be0b067908f682d260e3b9a056c8bf31cd544494cfa6ff36dc98639171cefc","source":{"kind":"arxiv","id":"2505.17338","version":2},"attestation_state":"computed","paper":{"title":"Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anwesa Choudhuri, Benjamin Planche, Meng Zheng, Terrence Chen, Zhongpai Gao, Ziyan Wu","submitted_at":"2025-05-22T23:18:30Z","abstract_excerpt":"Photorealistic volumetric rendering of CT scans greatly benefits clinical workflows, yet neural approaches such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) require prohibitive per-scan optimization (hours for NeRF, about 30 minutes for 3DGS), making them impractical in clinical settings. We propose Render-FM, a feedforward model that eliminates this bottleneck by directly regressing 6D Gaussian Splatting (6DGS) parameters from a CT volume in a single 2.8-second forward pass, a 500x speedup over per-scan optimization. To bridge the domain gap between natural scene reconstr"},"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":"2505.17338","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T23:18:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dd1f5899b11a9cc4d966087cb4a9d15853c8d8676275c0a89422cf230812c1a8","abstract_canon_sha256":"edf43cc75bdd3f13cedc7622a1c86ff870c3ace45944af00de429211ef4421da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:15.342066Z","signature_b64":"XYIF2MxafWVEmTQk8xjUmbglrw4qPBowZ3y+nfaBnISueEOdSUaGjmuT0OFNVb7q61qgILz9eSaEe2AWYfL2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06be0b067908f682d260e3b9a056c8bf31cd544494cfa6ff36dc98639171cefc","last_reissued_at":"2026-06-23T02:13:15.341654Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:15.341654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anwesa Choudhuri, Benjamin Planche, Meng Zheng, Terrence Chen, Zhongpai Gao, Ziyan Wu","submitted_at":"2025-05-22T23:18:30Z","abstract_excerpt":"Photorealistic volumetric rendering of CT scans greatly benefits clinical workflows, yet neural approaches such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) require prohibitive per-scan optimization (hours for NeRF, about 30 minutes for 3DGS), making them impractical in clinical settings. We propose Render-FM, a feedforward model that eliminates this bottleneck by directly regressing 6D Gaussian Splatting (6DGS) parameters from a CT volume in a single 2.8-second forward pass, a 500x speedup over per-scan optimization. To bridge the domain gap between natural scene reconstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17338","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/2505.17338/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":"2505.17338","created_at":"2026-06-23T02:13:15.341715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17338v2","created_at":"2026-06-23T02:13:15.341715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17338","created_at":"2026-06-23T02:13:15.341715+00:00"},{"alias_kind":"pith_short_12","alias_value":"A27AWBTZBD3I","created_at":"2026-06-23T02:13:15.341715+00:00"},{"alias_kind":"pith_short_16","alias_value":"A27AWBTZBD3IFUTA","created_at":"2026-06-23T02:13:15.341715+00:00"},{"alias_kind":"pith_short_8","alias_value":"A27AWBTZ","created_at":"2026-06-23T02:13:15.341715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2601.22026","citing_title":"Hybrid Foveated Path Tracing with Peripheral Gaussians for Immersive Anatomy","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A27AWBTZBD3IFUTA4O42AVWIX4","json":"https://pith.science/pith/A27AWBTZBD3IFUTA4O42AVWIX4.json","graph_json":"https://pith.science/api/pith-number/A27AWBTZBD3IFUTA4O42AVWIX4/graph.json","events_json":"https://pith.science/api/pith-number/A27AWBTZBD3IFUTA4O42AVWIX4/events.json","paper":"https://pith.science/paper/A27AWBTZ"},"agent_actions":{"view_html":"https://pith.science/pith/A27AWBTZBD3IFUTA4O42AVWIX4","download_json":"https://pith.science/pith/A27AWBTZBD3IFUTA4O42AVWIX4.json","view_paper":"https://pith.science/paper/A27AWBTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17338&json=true","fetch_graph":"https://pith.science/api/pith-number/A27AWBTZBD3IFUTA4O42AVWIX4/graph.json","fetch_events":"https://pith.science/api/pith-number/A27AWBTZBD3IFUTA4O42AVWIX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A27AWBTZBD3IFUTA4O42AVWIX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A27AWBTZBD3IFUTA4O42AVWIX4/action/storage_attestation","attest_author":"https://pith.science/pith/A27AWBTZBD3IFUTA4O42AVWIX4/action/author_attestation","sign_citation":"https://pith.science/pith/A27AWBTZBD3IFUTA4O42AVWIX4/action/citation_signature","submit_replication":"https://pith.science/pith/A27AWBTZBD3IFUTA4O42AVWIX4/action/replication_record"}},"created_at":"2026-06-23T02:13:15.341715+00:00","updated_at":"2026-06-23T02:13:15.341715+00:00"}