{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H3NORWFVJ4H7VVUN7PUKIXQBYV","short_pith_number":"pith:H3NORWFV","schema_version":"1.0","canonical_sha256":"3edae8d8b54f0ffad68dfbe8a45e01c5782dba2e15ecd3d96875e7d12b61751c","source":{"kind":"arxiv","id":"2410.24207","version":1},"attestation_state":"computed","paper":{"title":"No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botao Ye, Haofei Xu, Marc Pollefeys, Ming-Hsuan Yang, Sifei Liu, Songyou Peng, Xueting Li","submitted_at":"2024-10-31T17:58:22Z","abstract_excerpt":"We introduce NoPoSplat, a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from \\textit{unposed} sparse multi-view images. Our model, trained exclusively with photometric loss, achieves real-time 3D Gaussian reconstruction during inference. To eliminate the need for accurate pose input during reconstruction, we anchor one input view's local camera coordinates as the canonical space and train the network to predict Gaussian primitives for all views within this space. This approach obviates the need to transform Gaussian primitives from local coordinates into "},"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":"2410.24207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T17:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"1b9298f0d5885097f885b4c7380505319041011fef7c795bada38bf15e3e2230","abstract_canon_sha256":"e4a33a3a45026a97a1cafa227101e3ccbb67fe8591087711e0b520ab0a989dd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:21.257868Z","signature_b64":"ZUk5e9tiwQ97rbWl6a3rKOKCgyT8aqPSyhK/2KgoMzPtGhl2pPK/mmuSCnnPee+ppCPtX9bngl+1ffutRx/vDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3edae8d8b54f0ffad68dfbe8a45e01c5782dba2e15ecd3d96875e7d12b61751c","last_reissued_at":"2026-07-05T09:29:21.257338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:21.257338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botao Ye, Haofei Xu, Marc Pollefeys, Ming-Hsuan Yang, Sifei Liu, Songyou Peng, Xueting Li","submitted_at":"2024-10-31T17:58:22Z","abstract_excerpt":"We introduce NoPoSplat, a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from \\textit{unposed} sparse multi-view images. Our model, trained exclusively with photometric loss, achieves real-time 3D Gaussian reconstruction during inference. To eliminate the need for accurate pose input during reconstruction, we anchor one input view's local camera coordinates as the canonical space and train the network to predict Gaussian primitives for all views within this space. This approach obviates the need to transform Gaussian primitives from local coordinates into "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24207","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/2410.24207/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":"2410.24207","created_at":"2026-07-05T09:29:21.257411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.24207v1","created_at":"2026-07-05T09:29:21.257411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24207","created_at":"2026-07-05T09:29:21.257411+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3NORWFVJ4H7","created_at":"2026-07-05T09:29:21.257411+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3NORWFVJ4H7VVUN","created_at":"2026-07-05T09:29:21.257411+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3NORWFV","created_at":"2026-07-05T09:29:21.257411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":42,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07168","citing_title":"NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05347","citing_title":"WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27354","citing_title":"Error-Conditioned Neural Solvers","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23027","citing_title":"Learning Stable Canonical Worlds for Novel View Synthesis and Beyond","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02301","citing_title":"InvSplat: Inverse Feed-Forward Scene Splatting","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13644","citing_title":"Surflo: Consistent 3D Surface Flow Model with Global State","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10656","citing_title":"Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08980","citing_title":"EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05102","citing_title":"ZipSplat: Fewer Gaussians, Better Splats","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03499","citing_title":"Characterizing Detectability in 3DGS Poisoning: A Stage-wise Benchmark","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03254","citing_title":"OF$^3$GS: On-the-Fly Feed-Forward 3D Gaussian Splatting from Unposed Images","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30855","citing_title":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28321","citing_title":"StructSplat: Generalizable 3D Gaussian Splatting from Uncalibrated Sparse Views","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29374","citing_title":"L2D2-GS: Learning to Densify for Feedforward Dynamic Gaussian Scene Reconstruction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26115","citing_title":"TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31595","citing_title":"Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31535","citing_title":"RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14135","citing_title":"GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23888","citing_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23287","citing_title":"LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07287","citing_title":"SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16258","citing_title":"IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation","ref_index":17,"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":69,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16258","citing_title":"IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3NORWFVJ4H7VVUN7PUKIXQBYV","json":"https://pith.science/pith/H3NORWFVJ4H7VVUN7PUKIXQBYV.json","graph_json":"https://pith.science/api/pith-number/H3NORWFVJ4H7VVUN7PUKIXQBYV/graph.json","events_json":"https://pith.science/api/pith-number/H3NORWFVJ4H7VVUN7PUKIXQBYV/events.json","paper":"https://pith.science/paper/H3NORWFV"},"agent_actions":{"view_html":"https://pith.science/pith/H3NORWFVJ4H7VVUN7PUKIXQBYV","download_json":"https://pith.science/pith/H3NORWFVJ4H7VVUN7PUKIXQBYV.json","view_paper":"https://pith.science/paper/H3NORWFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.24207&json=true","fetch_graph":"https://pith.science/api/pith-number/H3NORWFVJ4H7VVUN7PUKIXQBYV/graph.json","fetch_events":"https://pith.science/api/pith-number/H3NORWFVJ4H7VVUN7PUKIXQBYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3NORWFVJ4H7VVUN7PUKIXQBYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3NORWFVJ4H7VVUN7PUKIXQBYV/action/storage_attestation","attest_author":"https://pith.science/pith/H3NORWFVJ4H7VVUN7PUKIXQBYV/action/author_attestation","sign_citation":"https://pith.science/pith/H3NORWFVJ4H7VVUN7PUKIXQBYV/action/citation_signature","submit_replication":"https://pith.science/pith/H3NORWFVJ4H7VVUN7PUKIXQBYV/action/replication_record"}},"created_at":"2026-07-05T09:29:21.257411+00:00","updated_at":"2026-07-05T09:29:21.257411+00:00"}