{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:67PZIJUSVAIN5CA7D36YAMFHEH","short_pith_number":"pith:67PZIJUS","schema_version":"1.0","canonical_sha256":"f7df942692a810de881f1efd8030a721c55c16d4bd292093940f869b9fbed511","source":{"kind":"arxiv","id":"2403.20309","version":6},"attestation_state":"computed","paper":{"title":"InstantSplat: Sparse-view Gaussian Splatting in Seconds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boris Ivanovic, Danfei Xu, Georgios Pavlakos, Jian Zhang, Kairun Wen, Kevin Wang, Marco Pavone, Wenyan Cong, Xinghao Ding, Yue Wang, Zhangyang Wang, Zhiwen Fan","submitted_at":"2024-03-29T17:29:58Z","abstract_excerpt":"While neural 3D reconstruction has advanced substantially, its performance significantly degrades with sparse-view data, which limits its broader applicability, since SfM is often unreliable in sparse-view scenarios where feature matches are scarce. In this paper, we introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed. InstantSplat employs a self-supervised framework that optimizes 3D scene representation and camera poses by unprojecting 2D pixels into 3D space and aligning them using differentiable neural rendering. The optimizat"},"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":"2403.20309","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T17:29:58Z","cross_cats_sorted":[],"title_canon_sha256":"4153c83462fa621e3c68e98e7ae2b26cdbec15766f243748f8b82b1d6805aa4e","abstract_canon_sha256":"cf4863151490224b5a3993c3c2c1b81f035d69dcb9c7b27bf76d3b6c44bb94f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:38.313011Z","signature_b64":"HBo89vMYtJAhIFVJpSLOPxmTwqmkYN+Baj5gOf62qrr/DdPc9V4dE7BoCPgmeKgdTcPhH5Gx0msqgcaEkYb7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7df942692a810de881f1efd8030a721c55c16d4bd292093940f869b9fbed511","last_reissued_at":"2026-07-05T11:31:38.312537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:38.312537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstantSplat: Sparse-view Gaussian Splatting in Seconds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boris Ivanovic, Danfei Xu, Georgios Pavlakos, Jian Zhang, Kairun Wen, Kevin Wang, Marco Pavone, Wenyan Cong, Xinghao Ding, Yue Wang, Zhangyang Wang, Zhiwen Fan","submitted_at":"2024-03-29T17:29:58Z","abstract_excerpt":"While neural 3D reconstruction has advanced substantially, its performance significantly degrades with sparse-view data, which limits its broader applicability, since SfM is often unreliable in sparse-view scenarios where feature matches are scarce. In this paper, we introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed. InstantSplat employs a self-supervised framework that optimizes 3D scene representation and camera poses by unprojecting 2D pixels into 3D space and aligning them using differentiable neural rendering. The optimizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20309","kind":"arxiv","version":6},"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/2403.20309/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":"2403.20309","created_at":"2026-07-05T11:31:38.312600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.20309v6","created_at":"2026-07-05T11:31:38.312600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20309","created_at":"2026-07-05T11:31:38.312600+00:00"},{"alias_kind":"pith_short_12","alias_value":"67PZIJUSVAIN","created_at":"2026-07-05T11:31:38.312600+00:00"},{"alias_kind":"pith_short_16","alias_value":"67PZIJUSVAIN5CA7","created_at":"2026-07-05T11:31:38.312600+00:00"},{"alias_kind":"pith_short_8","alias_value":"67PZIJUS","created_at":"2026-07-05T11:31:38.312600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"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":8,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23298","citing_title":"Ocean4D: Generative Underwater 4D Reconstruction via Medium-Aware Video Diffusion","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15966","citing_title":"VEPHand: View-Efficient Photometric Hand Performance Capture at Scale","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01556","citing_title":"Mind the Gap: Standard 3DGS Evaluation Primarily Measures Near-Trajectory Interpolation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05102","citing_title":"ZipSplat: Fewer Gaussians, Better Splats","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22020","citing_title":"ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2412.03077","citing_title":"RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2412.13547","citing_title":"Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22020","citing_title":"ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20155","citing_title":"GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16355","citing_title":"Generative 3D Gaussians with Learned Density Control","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09885","citing_title":"The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13122","citing_title":"DePT3R: Joint Dense Point Tracking and 3D Reconstruction of Dynamic Scenes in a Single Forward Pass","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2602.15355","citing_title":"DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20714","citing_title":"The Role of Initialization in 3D Gaussian Splatting","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14135","citing_title":"PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splatting","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26481","citing_title":"SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13093","citing_title":"RoSplat: Robust Feed-Forward Pixel-wise Gaussian Splatting for Varying Input Views and High-Resolution Rendering","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02048","citing_title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01479","citing_title":"UniRecGen: Unifying Multi-View 3D Reconstruction and Generation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02586","citing_title":"TrackerSplat: Exploiting Point Tracking for Fast and Robust Dynamic 3D Gaussians Reconstruction","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09024","citing_title":"Relightable Gaussian Splatting for Virtual Production Using Image-Based Illumination","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20155","citing_title":"GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11211","citing_title":"3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08718","citing_title":"Accelerating Transformer-Based Monocular SLAM via Geometric Utility Scoring","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67PZIJUSVAIN5CA7D36YAMFHEH","json":"https://pith.science/pith/67PZIJUSVAIN5CA7D36YAMFHEH.json","graph_json":"https://pith.science/api/pith-number/67PZIJUSVAIN5CA7D36YAMFHEH/graph.json","events_json":"https://pith.science/api/pith-number/67PZIJUSVAIN5CA7D36YAMFHEH/events.json","paper":"https://pith.science/paper/67PZIJUS"},"agent_actions":{"view_html":"https://pith.science/pith/67PZIJUSVAIN5CA7D36YAMFHEH","download_json":"https://pith.science/pith/67PZIJUSVAIN5CA7D36YAMFHEH.json","view_paper":"https://pith.science/paper/67PZIJUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.20309&json=true","fetch_graph":"https://pith.science/api/pith-number/67PZIJUSVAIN5CA7D36YAMFHEH/graph.json","fetch_events":"https://pith.science/api/pith-number/67PZIJUSVAIN5CA7D36YAMFHEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67PZIJUSVAIN5CA7D36YAMFHEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67PZIJUSVAIN5CA7D36YAMFHEH/action/storage_attestation","attest_author":"https://pith.science/pith/67PZIJUSVAIN5CA7D36YAMFHEH/action/author_attestation","sign_citation":"https://pith.science/pith/67PZIJUSVAIN5CA7D36YAMFHEH/action/citation_signature","submit_replication":"https://pith.science/pith/67PZIJUSVAIN5CA7D36YAMFHEH/action/replication_record"}},"created_at":"2026-07-05T11:31:38.312600+00:00","updated_at":"2026-07-05T11:31:38.312600+00:00"}