{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NYWPAVBWW2MVJRAWLQVTCZ4FNH","short_pith_number":"pith:NYWPAVBW","schema_version":"1.0","canonical_sha256":"6e2cf05436b69954c4165c2b31678569ee1049c259d88ec1aa412d67f6e223a7","source":{"kind":"arxiv","id":"2503.13176","version":3},"attestation_state":"computed","paper":{"title":"DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mirko Meboldt, Quentin Lohmeyer, Rui Wang, Siyu Tang","submitted_at":"2025-03-17T13:53:04Z","abstract_excerpt":"Reconstructing clean, distractor-free 3D scenes from real-world captures remains a significant challenge, particularly in highly dynamic and cluttered settings such as egocentric videos. To tackle this problem, we introduce DeGauss, a simple and robust self-supervised framework for dynamic scene reconstruction based on a decoupled dynamic-static Gaussian Splatting design. DeGauss models dynamic elements with foreground Gaussians and static content with background Gaussians, using a probabilistic mask to coordinate their composition and enable independent yet complementary optimization. DeGauss"},"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":"2503.13176","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T13:53:04Z","cross_cats_sorted":[],"title_canon_sha256":"ac04ffdbaf264da2c669ee6b04f2372bb6655ff5f44094ffd663ca4bb10db2e2","abstract_canon_sha256":"4c131b686b787b8f32cbaf4c44eacc6bec6a30a408fc769196a92ede82f76a75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:27.400686Z","signature_b64":"LvOicoK5SbZUN2Cy3KuFBsk+ynHhip8MqOW75sTXC+oNWS0tv++kAfIT/jqpb2EqJ8lgW5LEJsdxJgKMOKHMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e2cf05436b69954c4165c2b31678569ee1049c259d88ec1aa412d67f6e223a7","last_reissued_at":"2026-07-05T11:42:27.400176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:27.400176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mirko Meboldt, Quentin Lohmeyer, Rui Wang, Siyu Tang","submitted_at":"2025-03-17T13:53:04Z","abstract_excerpt":"Reconstructing clean, distractor-free 3D scenes from real-world captures remains a significant challenge, particularly in highly dynamic and cluttered settings such as egocentric videos. To tackle this problem, we introduce DeGauss, a simple and robust self-supervised framework for dynamic scene reconstruction based on a decoupled dynamic-static Gaussian Splatting design. DeGauss models dynamic elements with foreground Gaussians and static content with background Gaussians, using a probabilistic mask to coordinate their composition and enable independent yet complementary optimization. DeGauss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13176","kind":"arxiv","version":3},"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/2503.13176/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":"2503.13176","created_at":"2026-07-05T11:42:27.400237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13176v3","created_at":"2026-07-05T11:42:27.400237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13176","created_at":"2026-07-05T11:42:27.400237+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYWPAVBWW2MV","created_at":"2026-07-05T11:42:27.400237+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYWPAVBWW2MVJRAW","created_at":"2026-07-05T11:42:27.400237+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYWPAVBW","created_at":"2026-07-05T11:42:27.400237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23803","citing_title":"Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07986","citing_title":"DP-DeGauss: Dynamic Probabilistic Gaussian Decomposition for Egocentric 4D Scene Reconstruction","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NYWPAVBWW2MVJRAWLQVTCZ4FNH","json":"https://pith.science/pith/NYWPAVBWW2MVJRAWLQVTCZ4FNH.json","graph_json":"https://pith.science/api/pith-number/NYWPAVBWW2MVJRAWLQVTCZ4FNH/graph.json","events_json":"https://pith.science/api/pith-number/NYWPAVBWW2MVJRAWLQVTCZ4FNH/events.json","paper":"https://pith.science/paper/NYWPAVBW"},"agent_actions":{"view_html":"https://pith.science/pith/NYWPAVBWW2MVJRAWLQVTCZ4FNH","download_json":"https://pith.science/pith/NYWPAVBWW2MVJRAWLQVTCZ4FNH.json","view_paper":"https://pith.science/paper/NYWPAVBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13176&json=true","fetch_graph":"https://pith.science/api/pith-number/NYWPAVBWW2MVJRAWLQVTCZ4FNH/graph.json","fetch_events":"https://pith.science/api/pith-number/NYWPAVBWW2MVJRAWLQVTCZ4FNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYWPAVBWW2MVJRAWLQVTCZ4FNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYWPAVBWW2MVJRAWLQVTCZ4FNH/action/storage_attestation","attest_author":"https://pith.science/pith/NYWPAVBWW2MVJRAWLQVTCZ4FNH/action/author_attestation","sign_citation":"https://pith.science/pith/NYWPAVBWW2MVJRAWLQVTCZ4FNH/action/citation_signature","submit_replication":"https://pith.science/pith/NYWPAVBWW2MVJRAWLQVTCZ4FNH/action/replication_record"}},"created_at":"2026-07-05T11:42:27.400237+00:00","updated_at":"2026-07-05T11:42:27.400237+00:00"}