{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E4R6FQN3RC4DXPRMLIZQYAHFQ3","short_pith_number":"pith:E4R6FQN3","schema_version":"1.0","canonical_sha256":"2723e2c1bb88b83bbe2c5a330c00e586dc96d0e838bd90839b03b3aa1b3ede46","source":{"kind":"arxiv","id":"2503.10286","version":1},"attestation_state":"computed","paper":{"title":"VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengrui Dong, Peidong Liu, Yiming Chen, Zhangchi Huang, Zhiqi Li","submitted_at":"2025-03-13T11:56:05Z","abstract_excerpt":"We present VicaSplat, a novel framework for joint 3D Gaussians reconstruction and camera pose estimation from a sequence of unposed video frames, which is a critical yet underexplored task in real-world 3D applications. The core of our method lies in a novel transformer-based network architecture. In particular, our model starts with an image encoder that maps each image to a list of visual tokens. All visual tokens are concatenated with additional inserted learnable camera tokens. The obtained tokens then fully communicate with each other within a tailored transformer decoder. The camera toke"},"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":"2503.10286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T11:56:05Z","cross_cats_sorted":[],"title_canon_sha256":"15ebdcb846ffeb07af2c298d3dea671bd3d434daaf776d2e7153bc1dfea83670","abstract_canon_sha256":"54ee800d5686558a721abc15e510e3c467005879048864e2f831f97dc92afea2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:42.183046Z","signature_b64":"kL8RszfYxkp7bP2aEiT0ilngqWbnGZ3A7tTYHOx0FuI8nhe4VNoX6T/6T/gvHjbovqdzpFF/9n4H8AMGLMQTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2723e2c1bb88b83bbe2c5a330c00e586dc96d0e838bd90839b03b3aa1b3ede46","last_reissued_at":"2026-07-05T10:30:42.182184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:42.182184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengrui Dong, Peidong Liu, Yiming Chen, Zhangchi Huang, Zhiqi Li","submitted_at":"2025-03-13T11:56:05Z","abstract_excerpt":"We present VicaSplat, a novel framework for joint 3D Gaussians reconstruction and camera pose estimation from a sequence of unposed video frames, which is a critical yet underexplored task in real-world 3D applications. The core of our method lies in a novel transformer-based network architecture. In particular, our model starts with an image encoder that maps each image to a list of visual tokens. All visual tokens are concatenated with additional inserted learnable camera tokens. The obtained tokens then fully communicate with each other within a tailored transformer decoder. The camera toke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10286","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/2503.10286/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":"2503.10286","created_at":"2026-07-05T10:30:42.182309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10286v1","created_at":"2026-07-05T10:30:42.182309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10286","created_at":"2026-07-05T10:30:42.182309+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4R6FQN3RC4D","created_at":"2026-07-05T10:30:42.182309+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4R6FQN3RC4DXPRM","created_at":"2026-07-05T10:30:42.182309+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4R6FQN3","created_at":"2026-07-05T10:30:42.182309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03254","citing_title":"OF$^3$GS: On-the-Fly Feed-Forward 3D Gaussian Splatting from Unposed Images","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30045","citing_title":"Walking in the Implicit: Interactive World Exploration via Neural Scene Representation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31535","citing_title":"RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10239","citing_title":"AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10239","citing_title":"AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10573","citing_title":"Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4R6FQN3RC4DXPRMLIZQYAHFQ3","json":"https://pith.science/pith/E4R6FQN3RC4DXPRMLIZQYAHFQ3.json","graph_json":"https://pith.science/api/pith-number/E4R6FQN3RC4DXPRMLIZQYAHFQ3/graph.json","events_json":"https://pith.science/api/pith-number/E4R6FQN3RC4DXPRMLIZQYAHFQ3/events.json","paper":"https://pith.science/paper/E4R6FQN3"},"agent_actions":{"view_html":"https://pith.science/pith/E4R6FQN3RC4DXPRMLIZQYAHFQ3","download_json":"https://pith.science/pith/E4R6FQN3RC4DXPRMLIZQYAHFQ3.json","view_paper":"https://pith.science/paper/E4R6FQN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10286&json=true","fetch_graph":"https://pith.science/api/pith-number/E4R6FQN3RC4DXPRMLIZQYAHFQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/E4R6FQN3RC4DXPRMLIZQYAHFQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4R6FQN3RC4DXPRMLIZQYAHFQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4R6FQN3RC4DXPRMLIZQYAHFQ3/action/storage_attestation","attest_author":"https://pith.science/pith/E4R6FQN3RC4DXPRMLIZQYAHFQ3/action/author_attestation","sign_citation":"https://pith.science/pith/E4R6FQN3RC4DXPRMLIZQYAHFQ3/action/citation_signature","submit_replication":"https://pith.science/pith/E4R6FQN3RC4DXPRMLIZQYAHFQ3/action/replication_record"}},"created_at":"2026-07-05T10:30:42.182309+00:00","updated_at":"2026-07-05T10:30:42.182309+00:00"}