{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KZ2ZKILRSGLZVODIBX4RYNOZ2L","short_pith_number":"pith:KZ2ZKILR","schema_version":"1.0","canonical_sha256":"567595217191979ab8680df91c35d9d2cdfb967e52c017a6911124fc967c88f5","source":{"kind":"arxiv","id":"2312.12337","version":4},"attestation_state":"computed","paper":{"title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrea Tagliasacchi, David Charatan, Sizhe Li, Vincent Sitzmann","submitted_at":"2023-12-19T17:03:50Z","abstract_excerpt":"We introduce pixelSplat, a feed-forward model that learns to reconstruct 3D radiance fields parameterized by 3D Gaussian primitives from pairs of images. Our model features real-time and memory-efficient rendering for scalable training as well as fast 3D reconstruction at inference time. To overcome local minima inherent to sparse and locally supported representations, we predict a dense probability distribution over 3D and sample Gaussian means from that probability distribution. We make this sampling operation differentiable via a reparameterization trick, allowing us to back-propagate gradi"},"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":"2312.12337","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T17:03:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"10f1c42bd11a0c5255b8a3973869198a1258b34eda45584ad044f0e5f624d649","abstract_canon_sha256":"165958484fc0d3827fdc877e4abb1a3a0707aa0ce58e97c31548ab252d0517fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:36.425690Z","signature_b64":"/bM/cOvt8moxixS1FX/YDbaWGSkDYzZ1QynK49uPpPvod5uxkFV11xjgPod38J5OFZhfWp1WTYqYI9Dt3c+BDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"567595217191979ab8680df91c35d9d2cdfb967e52c017a6911124fc967c88f5","last_reissued_at":"2026-07-05T08:04:36.425266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:36.425266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrea Tagliasacchi, David Charatan, Sizhe Li, Vincent Sitzmann","submitted_at":"2023-12-19T17:03:50Z","abstract_excerpt":"We introduce pixelSplat, a feed-forward model that learns to reconstruct 3D radiance fields parameterized by 3D Gaussian primitives from pairs of images. Our model features real-time and memory-efficient rendering for scalable training as well as fast 3D reconstruction at inference time. To overcome local minima inherent to sparse and locally supported representations, we predict a dense probability distribution over 3D and sample Gaussian means from that probability distribution. We make this sampling operation differentiable via a reparameterization trick, allowing us to back-propagate gradi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12337","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/2312.12337/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":"2312.12337","created_at":"2026-07-05T08:04:36.425321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12337v4","created_at":"2026-07-05T08:04:36.425321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12337","created_at":"2026-07-05T08:04:36.425321+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZ2ZKILRSGLZ","created_at":"2026-07-05T08:04:36.425321+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZ2ZKILRSGLZVODI","created_at":"2026-07-05T08:04:36.425321+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZ2ZKILR","created_at":"2026-07-05T08:04:36.425321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26158","citing_title":"Life After Benchmark Saturation: A Case Study of CORE-Bench","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01803","citing_title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05912","citing_title":"Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29976","citing_title":"Learning Efficient 4D Gaussian Representations from Monocular Videos with Flow Splatting","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23888","citing_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22190","citing_title":"No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02509","citing_title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZ2ZKILRSGLZVODIBX4RYNOZ2L","json":"https://pith.science/pith/KZ2ZKILRSGLZVODIBX4RYNOZ2L.json","graph_json":"https://pith.science/api/pith-number/KZ2ZKILRSGLZVODIBX4RYNOZ2L/graph.json","events_json":"https://pith.science/api/pith-number/KZ2ZKILRSGLZVODIBX4RYNOZ2L/events.json","paper":"https://pith.science/paper/KZ2ZKILR"},"agent_actions":{"view_html":"https://pith.science/pith/KZ2ZKILRSGLZVODIBX4RYNOZ2L","download_json":"https://pith.science/pith/KZ2ZKILRSGLZVODIBX4RYNOZ2L.json","view_paper":"https://pith.science/paper/KZ2ZKILR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12337&json=true","fetch_graph":"https://pith.science/api/pith-number/KZ2ZKILRSGLZVODIBX4RYNOZ2L/graph.json","fetch_events":"https://pith.science/api/pith-number/KZ2ZKILRSGLZVODIBX4RYNOZ2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZ2ZKILRSGLZVODIBX4RYNOZ2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZ2ZKILRSGLZVODIBX4RYNOZ2L/action/storage_attestation","attest_author":"https://pith.science/pith/KZ2ZKILRSGLZVODIBX4RYNOZ2L/action/author_attestation","sign_citation":"https://pith.science/pith/KZ2ZKILRSGLZVODIBX4RYNOZ2L/action/citation_signature","submit_replication":"https://pith.science/pith/KZ2ZKILRSGLZVODIBX4RYNOZ2L/action/replication_record"}},"created_at":"2026-07-05T08:04:36.425321+00:00","updated_at":"2026-07-05T08:04:36.425321+00:00"}