{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NSTA57FV5VJY6UIMF7ONO75Z4A","short_pith_number":"pith:NSTA57FV","schema_version":"1.0","canonical_sha256":"6ca60efcb5ed538f510c2fdcd77fb9e0106df28d6a58696437add29b19dd2943","source":{"kind":"arxiv","id":"2410.17242","version":2},"attestation_state":"computed","paper":{"title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fujun Luan, Haian Jin, Hanwen Jiang, Hao Tan, Kai Zhang, Noah Snavely, Sai Bi, Tianyuan Zhang, Zexiang Xu","submitted_at":"2024-10-22T17:58:28Z","abstract_excerpt":"We propose the Large View Synthesis Model (LVSM), a novel transformer-based approach for scalable and generalizable novel view synthesis from sparse-view inputs. We introduce two architectures: (1) an encoder-decoder LVSM, which encodes input image tokens into a fixed number of 1D latent tokens, functioning as a fully learned scene representation, and decodes novel-view images from them; and (2) a decoder-only LVSM, which directly maps input images to novel-view outputs, completely eliminating intermediate scene representations. Both models bypass the 3D inductive biases used in previous metho"},"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":"2410.17242","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-22T17:58:28Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"af1cf393473ee85a3034cdb4c0f02814ba3b81cc9477aebdf56880ff3c4651b8","abstract_canon_sha256":"3bbd0bd639796fd47152f76baeee887cdb1fbe38f667edf858ffc4e2eb99d709"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:40.478484Z","signature_b64":"6Qkx/htC4MpdOQn08AHd6GyV5LsXjbMFyE1j6BIJv/yL0p1Xh4OC1pXg5aD5j56Mjt4iy8KQ4Cf4c1/M3A2sCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ca60efcb5ed538f510c2fdcd77fb9e0106df28d6a58696437add29b19dd2943","last_reissued_at":"2026-07-05T10:43:40.478010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:40.478010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fujun Luan, Haian Jin, Hanwen Jiang, Hao Tan, Kai Zhang, Noah Snavely, Sai Bi, Tianyuan Zhang, Zexiang Xu","submitted_at":"2024-10-22T17:58:28Z","abstract_excerpt":"We propose the Large View Synthesis Model (LVSM), a novel transformer-based approach for scalable and generalizable novel view synthesis from sparse-view inputs. We introduce two architectures: (1) an encoder-decoder LVSM, which encodes input image tokens into a fixed number of 1D latent tokens, functioning as a fully learned scene representation, and decodes novel-view images from them; and (2) a decoder-only LVSM, which directly maps input images to novel-view outputs, completely eliminating intermediate scene representations. Both models bypass the 3D inductive biases used in previous metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17242","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/2410.17242/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":"2410.17242","created_at":"2026-07-05T10:43:40.478066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17242v2","created_at":"2026-07-05T10:43:40.478066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17242","created_at":"2026-07-05T10:43:40.478066+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSTA57FV5VJY","created_at":"2026-07-05T10:43:40.478066+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSTA57FV5VJY6UIM","created_at":"2026-07-05T10:43:40.478066+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSTA57FV","created_at":"2026-07-05T10:43:40.478066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07168","citing_title":"NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24876","citing_title":"FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10025","citing_title":"GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06624","citing_title":"Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31585","citing_title":"DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31258","citing_title":"WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22481","citing_title":"Lighting-Consistent Object Transfer Across Radiance Fields","ref_index":240,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14671","citing_title":"ART: Articulated Reconstruction Transformer","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18735","citing_title":"PIXLRelight: Controllable Relighting via Intrinsic Conditioning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00978","citing_title":"A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10267","citing_title":"Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23884","citing_title":"Test-Time Training Done Right","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08712","citing_title":"From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18747","citing_title":"URoPE: Universal Relative Position Embedding across Geometric Spaces","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10259","citing_title":"Real-Time Human Reconstruction and Animation using Feed-Forward Gaussian Splatting","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11331","citing_title":"Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10512","citing_title":"FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08500","citing_title":"Novel View Synthesis as Video Completion","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05182","citing_title":"LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04707","citing_title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15239","citing_title":"TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15284","citing_title":"GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NSTA57FV5VJY6UIMF7ONO75Z4A","json":"https://pith.science/pith/NSTA57FV5VJY6UIMF7ONO75Z4A.json","graph_json":"https://pith.science/api/pith-number/NSTA57FV5VJY6UIMF7ONO75Z4A/graph.json","events_json":"https://pith.science/api/pith-number/NSTA57FV5VJY6UIMF7ONO75Z4A/events.json","paper":"https://pith.science/paper/NSTA57FV"},"agent_actions":{"view_html":"https://pith.science/pith/NSTA57FV5VJY6UIMF7ONO75Z4A","download_json":"https://pith.science/pith/NSTA57FV5VJY6UIMF7ONO75Z4A.json","view_paper":"https://pith.science/paper/NSTA57FV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17242&json=true","fetch_graph":"https://pith.science/api/pith-number/NSTA57FV5VJY6UIMF7ONO75Z4A/graph.json","fetch_events":"https://pith.science/api/pith-number/NSTA57FV5VJY6UIMF7ONO75Z4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSTA57FV5VJY6UIMF7ONO75Z4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSTA57FV5VJY6UIMF7ONO75Z4A/action/storage_attestation","attest_author":"https://pith.science/pith/NSTA57FV5VJY6UIMF7ONO75Z4A/action/author_attestation","sign_citation":"https://pith.science/pith/NSTA57FV5VJY6UIMF7ONO75Z4A/action/citation_signature","submit_replication":"https://pith.science/pith/NSTA57FV5VJY6UIMF7ONO75Z4A/action/replication_record"}},"created_at":"2026-07-05T10:43:40.478066+00:00","updated_at":"2026-07-05T10:43:40.478066+00:00"}