{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6D56DSMPTNKMLBNLVZZMOBK576","short_pith_number":"pith:6D56DSMP","schema_version":"1.0","canonical_sha256":"f0fbe1c98f9b54c585abae72c7055dff86630ce374209ab2a4323886b141a1c2","source":{"kind":"arxiv","id":"2403.14621","version":1},"attestation_state":"computed","paper":{"title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ceyuan Yang, Gordon Wetzstein, Hansheng Chen, Sida Peng, Wang Yifan, Yinghao Xu, Yujun Shen, Zifan Shi","submitted_at":"2024-03-21T17:59:34Z","abstract_excerpt":"We introduce GRM, a large-scale reconstructor capable of recovering a 3D asset from sparse-view images in around 0.1s. GRM is a feed-forward transformer-based model that efficiently incorporates multi-view information to translate the input pixels into pixel-aligned Gaussians, which are unprojected to create a set of densely distributed 3D Gaussians representing a scene. Together, our transformer architecture and the use of 3D Gaussians unlock a scalable and efficient reconstruction framework. Extensive experimental results demonstrate the superiority of our method over alternatives regarding "},"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":"2403.14621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T17:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"00b6974ef4a99d3315ff699bb9d1c68a87d2cc77b1dd7ae885993bbdec09e73b","abstract_canon_sha256":"196363f0e17f28a9088d13918025c897243c9d8b71a44c21717ab82af2aa5f66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:11.588324Z","signature_b64":"uF4psrTYg4n53jCtR873DPddo6j+fpSMj6touBD/pq8YZzWNxSCw2k/AufIqMP4+Z2yE29Amgxpv5TA3rTSXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0fbe1c98f9b54c585abae72c7055dff86630ce374209ab2a4323886b141a1c2","last_reissued_at":"2026-07-05T07:59:11.587858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:11.587858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ceyuan Yang, Gordon Wetzstein, Hansheng Chen, Sida Peng, Wang Yifan, Yinghao Xu, Yujun Shen, Zifan Shi","submitted_at":"2024-03-21T17:59:34Z","abstract_excerpt":"We introduce GRM, a large-scale reconstructor capable of recovering a 3D asset from sparse-view images in around 0.1s. GRM is a feed-forward transformer-based model that efficiently incorporates multi-view information to translate the input pixels into pixel-aligned Gaussians, which are unprojected to create a set of densely distributed 3D Gaussians representing a scene. Together, our transformer architecture and the use of 3D Gaussians unlock a scalable and efficient reconstruction framework. Extensive experimental results demonstrate the superiority of our method over alternatives regarding "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14621","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/2403.14621/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":"2403.14621","created_at":"2026-07-05T07:59:11.587913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14621v1","created_at":"2026-07-05T07:59:11.587913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14621","created_at":"2026-07-05T07:59:11.587913+00:00"},{"alias_kind":"pith_short_12","alias_value":"6D56DSMPTNKM","created_at":"2026-07-05T07:59:11.587913+00:00"},{"alias_kind":"pith_short_16","alias_value":"6D56DSMPTNKMLBNL","created_at":"2026-07-05T07:59:11.587913+00:00"},{"alias_kind":"pith_short_8","alias_value":"6D56DSMP","created_at":"2026-07-05T07:59:11.587913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01803","citing_title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32036","citing_title":"PointSplat: Compact Gaussian Splatting via Human-Centric Prediction","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31109","citing_title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31466","citing_title":"VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22481","citing_title":"Lighting-Consistent Object Transfer Across Radiance Fields","ref_index":264,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":257,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07603","citing_title":"UIKA: Fast Universal Head Avatar from Pose-Free Images","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21121","citing_title":"ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18132","citing_title":"Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18365","citing_title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07435","citing_title":"DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24591","citing_title":"Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2404.07191","citing_title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6D56DSMPTNKMLBNLVZZMOBK576","json":"https://pith.science/pith/6D56DSMPTNKMLBNLVZZMOBK576.json","graph_json":"https://pith.science/api/pith-number/6D56DSMPTNKMLBNLVZZMOBK576/graph.json","events_json":"https://pith.science/api/pith-number/6D56DSMPTNKMLBNLVZZMOBK576/events.json","paper":"https://pith.science/paper/6D56DSMP"},"agent_actions":{"view_html":"https://pith.science/pith/6D56DSMPTNKMLBNLVZZMOBK576","download_json":"https://pith.science/pith/6D56DSMPTNKMLBNLVZZMOBK576.json","view_paper":"https://pith.science/paper/6D56DSMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14621&json=true","fetch_graph":"https://pith.science/api/pith-number/6D56DSMPTNKMLBNLVZZMOBK576/graph.json","fetch_events":"https://pith.science/api/pith-number/6D56DSMPTNKMLBNLVZZMOBK576/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6D56DSMPTNKMLBNLVZZMOBK576/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6D56DSMPTNKMLBNLVZZMOBK576/action/storage_attestation","attest_author":"https://pith.science/pith/6D56DSMPTNKMLBNLVZZMOBK576/action/author_attestation","sign_citation":"https://pith.science/pith/6D56DSMPTNKMLBNLVZZMOBK576/action/citation_signature","submit_replication":"https://pith.science/pith/6D56DSMPTNKMLBNLVZZMOBK576/action/replication_record"}},"created_at":"2026-07-05T07:59:11.587913+00:00","updated_at":"2026-07-05T07:59:11.587913+00:00"}