{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G2FIUIHQJIM3TCNBHIHT5EG26X","short_pith_number":"pith:G2FIUIHQ","schema_version":"1.0","canonical_sha256":"368a8a20f04a19b989a13a0f3e90daf5c33d4d052f23b20091a134f1556e21b7","source":{"kind":"arxiv","id":"2412.16346","version":2},"attestation_state":"computed","paper":{"title":"SOUS VIDE: Cooking Visual Drone Navigation Policies in a Gaussian Splatting Vacuum","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Javier Yu, JunEn Low, Keiko Nagami, Mac Schwager, Maximilian Adang","submitted_at":"2024-12-20T21:13:11Z","abstract_excerpt":"We propose a new simulator, training approach, and policy architecture, collectively called SOUS VIDE, for end-to-end visual drone navigation. Our trained policies exhibit zero-shot sim-to-real transfer with robust real-world performance using only onboard perception and computation. Our simulator, called FiGS, couples a computationally simple drone dynamics model with a high visual fidelity Gaussian Splatting scene reconstruction. FiGS can quickly simulate drone flights producing photorealistic images at up to 130 fps. We use FiGS to collect 100k-300k image/state-action pairs from an expert M"},"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":"2412.16346","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-20T21:13:11Z","cross_cats_sorted":["cs.CV","cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"4b95c76e11b31f756d58997d23539d08e2d0f0ee1dc01c3f947b6a7470a3be9c","abstract_canon_sha256":"d378b637185e2e6dbb7877e21d60cbc93fa0c3708be93b1f0cd5a243eeeed33d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:33.442759Z","signature_b64":"PygjChxGkBj6/ZtQDqmQXseryjMw92lWRQQ1ykAoDVZD0udNtyY9RnQQXzrbz3P/gRi6nZFFw9fUZc/XRXm7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"368a8a20f04a19b989a13a0f3e90daf5c33d4d052f23b20091a134f1556e21b7","last_reissued_at":"2026-07-05T10:36:33.441874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:33.441874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOUS VIDE: Cooking Visual Drone Navigation Policies in a Gaussian Splatting Vacuum","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Javier Yu, JunEn Low, Keiko Nagami, Mac Schwager, Maximilian Adang","submitted_at":"2024-12-20T21:13:11Z","abstract_excerpt":"We propose a new simulator, training approach, and policy architecture, collectively called SOUS VIDE, for end-to-end visual drone navigation. Our trained policies exhibit zero-shot sim-to-real transfer with robust real-world performance using only onboard perception and computation. Our simulator, called FiGS, couples a computationally simple drone dynamics model with a high visual fidelity Gaussian Splatting scene reconstruction. FiGS can quickly simulate drone flights producing photorealistic images at up to 130 fps. We use FiGS to collect 100k-300k image/state-action pairs from an expert M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16346","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/2412.16346/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":"2412.16346","created_at":"2026-07-05T10:36:33.442002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16346v2","created_at":"2026-07-05T10:36:33.442002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16346","created_at":"2026-07-05T10:36:33.442002+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2FIUIHQJIM3","created_at":"2026-07-05T10:36:33.442002+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2FIUIHQJIM3TCNB","created_at":"2026-07-05T10:36:33.442002+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2FIUIHQ","created_at":"2026-07-05T10:36:33.442002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29783","citing_title":"FalconTrack: Photorealistic Auto-Labeled Perception and Physics-Aware Vision-Based Aerial Tracking","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14009","citing_title":"GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G2FIUIHQJIM3TCNBHIHT5EG26X","json":"https://pith.science/pith/G2FIUIHQJIM3TCNBHIHT5EG26X.json","graph_json":"https://pith.science/api/pith-number/G2FIUIHQJIM3TCNBHIHT5EG26X/graph.json","events_json":"https://pith.science/api/pith-number/G2FIUIHQJIM3TCNBHIHT5EG26X/events.json","paper":"https://pith.science/paper/G2FIUIHQ"},"agent_actions":{"view_html":"https://pith.science/pith/G2FIUIHQJIM3TCNBHIHT5EG26X","download_json":"https://pith.science/pith/G2FIUIHQJIM3TCNBHIHT5EG26X.json","view_paper":"https://pith.science/paper/G2FIUIHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16346&json=true","fetch_graph":"https://pith.science/api/pith-number/G2FIUIHQJIM3TCNBHIHT5EG26X/graph.json","fetch_events":"https://pith.science/api/pith-number/G2FIUIHQJIM3TCNBHIHT5EG26X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2FIUIHQJIM3TCNBHIHT5EG26X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2FIUIHQJIM3TCNBHIHT5EG26X/action/storage_attestation","attest_author":"https://pith.science/pith/G2FIUIHQJIM3TCNBHIHT5EG26X/action/author_attestation","sign_citation":"https://pith.science/pith/G2FIUIHQJIM3TCNBHIHT5EG26X/action/citation_signature","submit_replication":"https://pith.science/pith/G2FIUIHQJIM3TCNBHIHT5EG26X/action/replication_record"}},"created_at":"2026-07-05T10:36:33.442002+00:00","updated_at":"2026-07-05T10:36:33.442002+00:00"}