{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7G2AVHHWYLDZXQN2VG3I6W74JS","short_pith_number":"pith:7G2AVHHW","schema_version":"1.0","canonical_sha256":"f9b40a9cf6c2c79bc1baa9b68f5bfc4c87babd69c40461fbbca59bceffde929e","source":{"kind":"arxiv","id":"2204.02296","version":2},"attestation_state":"computed","paper":{"title":"iSDF: Real-Time Neural Signed Distance Fields for Robot Perception","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Alexander Clegg, David Novotny, Edgar Sucar, Jing Dong, Joseph Ortiz, Michael Zollhoefer, Mustafa Mukadam","submitted_at":"2022-04-05T15:48:39Z","abstract_excerpt":"We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction. Given a stream of posed depth images from a moving camera, it trains a randomly initialised neural network to map input 3D coordinate to approximate signed distance. The model is self-supervised by minimising a loss that bounds the predicted signed distance using the distance to the closest sampled point in a batch of query points that are actively sampled. In contrast to prior work based on voxel grids, our neural method is able to provide adaptive levels of detail with plausible filling in "},"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":"2204.02296","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2022-04-05T15:48:39Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6803ee448f75280b148b91cc81f38ccc55c6040c97a0e365cd3cecdd1a970947","abstract_canon_sha256":"373e513829277f965dce664003f4ccd4ade63e7258a0fdc2aba1de0603f21bd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:19.504205Z","signature_b64":"LzfHGWmTkf2GOvYFsMF+w9FYQ4IVfT6JSg2DCrZdiNnwj9QeCnsYY8IASkIY0Y/uptF6tliOcqg5BV1xjWAdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9b40a9cf6c2c79bc1baa9b68f5bfc4c87babd69c40461fbbca59bceffde929e","last_reissued_at":"2026-07-05T04:20:19.503752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:19.503752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iSDF: Real-Time Neural Signed Distance Fields for Robot Perception","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Alexander Clegg, David Novotny, Edgar Sucar, Jing Dong, Joseph Ortiz, Michael Zollhoefer, Mustafa Mukadam","submitted_at":"2022-04-05T15:48:39Z","abstract_excerpt":"We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction. Given a stream of posed depth images from a moving camera, it trains a randomly initialised neural network to map input 3D coordinate to approximate signed distance. The model is self-supervised by minimising a loss that bounds the predicted signed distance using the distance to the closest sampled point in a batch of query points that are actively sampled. In contrast to prior work based on voxel grids, our neural method is able to provide adaptive levels of detail with plausible filling in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02296","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/2204.02296/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":"2204.02296","created_at":"2026-07-05T04:20:19.503811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02296v2","created_at":"2026-07-05T04:20:19.503811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02296","created_at":"2026-07-05T04:20:19.503811+00:00"},{"alias_kind":"pith_short_12","alias_value":"7G2AVHHWYLDZ","created_at":"2026-07-05T04:20:19.503811+00:00"},{"alias_kind":"pith_short_16","alias_value":"7G2AVHHWYLDZXQN2","created_at":"2026-07-05T04:20:19.503811+00:00"},{"alias_kind":"pith_short_8","alias_value":"7G2AVHHW","created_at":"2026-07-05T04:20:19.503811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18426","citing_title":"VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21258","citing_title":"Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04525","citing_title":"G-EDF-Loc: 3D Continuous Gaussian Distance Field for Robust Gradient-Based 6DoF Localization","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7G2AVHHWYLDZXQN2VG3I6W74JS","json":"https://pith.science/pith/7G2AVHHWYLDZXQN2VG3I6W74JS.json","graph_json":"https://pith.science/api/pith-number/7G2AVHHWYLDZXQN2VG3I6W74JS/graph.json","events_json":"https://pith.science/api/pith-number/7G2AVHHWYLDZXQN2VG3I6W74JS/events.json","paper":"https://pith.science/paper/7G2AVHHW"},"agent_actions":{"view_html":"https://pith.science/pith/7G2AVHHWYLDZXQN2VG3I6W74JS","download_json":"https://pith.science/pith/7G2AVHHWYLDZXQN2VG3I6W74JS.json","view_paper":"https://pith.science/paper/7G2AVHHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02296&json=true","fetch_graph":"https://pith.science/api/pith-number/7G2AVHHWYLDZXQN2VG3I6W74JS/graph.json","fetch_events":"https://pith.science/api/pith-number/7G2AVHHWYLDZXQN2VG3I6W74JS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7G2AVHHWYLDZXQN2VG3I6W74JS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7G2AVHHWYLDZXQN2VG3I6W74JS/action/storage_attestation","attest_author":"https://pith.science/pith/7G2AVHHWYLDZXQN2VG3I6W74JS/action/author_attestation","sign_citation":"https://pith.science/pith/7G2AVHHWYLDZXQN2VG3I6W74JS/action/citation_signature","submit_replication":"https://pith.science/pith/7G2AVHHWYLDZXQN2VG3I6W74JS/action/replication_record"}},"created_at":"2026-07-05T04:20:19.503811+00:00","updated_at":"2026-07-05T04:20:19.503811+00:00"}