{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GOLPT2QRJQPLZIHOOBSN6C7ZLS","short_pith_number":"pith:GOLPT2QR","schema_version":"1.0","canonical_sha256":"3396f9ea114c1ebca0ee7064df0bf95cbffc04da74bc032553e0b262b09c3cda","source":{"kind":"arxiv","id":"2412.02493","version":1},"attestation_state":"computed","paper":{"title":"RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengxiang Wen, Jian Zhang, Jiarui Meng, Jie Chen, Luyang Tang, Qiankun Gao, Ronggang Wang, Yanmin Wu","submitted_at":"2024-12-03T15:08:03Z","abstract_excerpt":"Reconstructing dynamic scenes with large-scale and complex motions remains a significant challenge. Recent techniques like Neural Radiance Fields and 3D Gaussian Splatting (3DGS) have shown promise but still struggle with scenes involving substantial movement. This paper proposes RelayGS, a novel method based on 3DGS, specifically designed to represent and reconstruct highly dynamic scenes. Our RelayGS learns a complete 4D representation with canonical 3D Gaussians and a compact motion field, consisting of three stages. First, we learn a fundamental 3DGS from all frames, ignoring temporal scen"},"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":"2412.02493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T15:08:03Z","cross_cats_sorted":[],"title_canon_sha256":"98c4b0d6849a2630bf1a56a9a39b5e35b361b0a4191e2e67b0e68c5521ca8129","abstract_canon_sha256":"fd75d3b992f243f45b1b37ce9c445d48894637f59f45263c345de67f764df0dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:50.701548Z","signature_b64":"FWxsR+ubXDdBL6V9eeP3unfJw5u6x3oCZd2vYuwR0gOgSc6v47XRvx9PuAWgPPYZ24rp3nEV2393L960P/JKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3396f9ea114c1ebca0ee7064df0bf95cbffc04da74bc032553e0b262b09c3cda","last_reissued_at":"2026-07-05T09:43:50.701038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:50.701038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengxiang Wen, Jian Zhang, Jiarui Meng, Jie Chen, Luyang Tang, Qiankun Gao, Ronggang Wang, Yanmin Wu","submitted_at":"2024-12-03T15:08:03Z","abstract_excerpt":"Reconstructing dynamic scenes with large-scale and complex motions remains a significant challenge. Recent techniques like Neural Radiance Fields and 3D Gaussian Splatting (3DGS) have shown promise but still struggle with scenes involving substantial movement. This paper proposes RelayGS, a novel method based on 3DGS, specifically designed to represent and reconstruct highly dynamic scenes. Our RelayGS learns a complete 4D representation with canonical 3D Gaussians and a compact motion field, consisting of three stages. First, we learn a fundamental 3DGS from all frames, ignoring temporal scen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02493","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/2412.02493/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":"2412.02493","created_at":"2026-07-05T09:43:50.701099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02493v1","created_at":"2026-07-05T09:43:50.701099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02493","created_at":"2026-07-05T09:43:50.701099+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOLPT2QRJQPL","created_at":"2026-07-05T09:43:50.701099+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOLPT2QRJQPLZIHO","created_at":"2026-07-05T09:43:50.701099+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOLPT2QR","created_at":"2026-07-05T09:43:50.701099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11427","citing_title":"PD-4DGS:Progressive Decomposition of 4D Gaussian Splatting for Bandwidth-Adaptive Dynamic Scene Streaming","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23803","citing_title":"Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOLPT2QRJQPLZIHOOBSN6C7ZLS","json":"https://pith.science/pith/GOLPT2QRJQPLZIHOOBSN6C7ZLS.json","graph_json":"https://pith.science/api/pith-number/GOLPT2QRJQPLZIHOOBSN6C7ZLS/graph.json","events_json":"https://pith.science/api/pith-number/GOLPT2QRJQPLZIHOOBSN6C7ZLS/events.json","paper":"https://pith.science/paper/GOLPT2QR"},"agent_actions":{"view_html":"https://pith.science/pith/GOLPT2QRJQPLZIHOOBSN6C7ZLS","download_json":"https://pith.science/pith/GOLPT2QRJQPLZIHOOBSN6C7ZLS.json","view_paper":"https://pith.science/paper/GOLPT2QR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02493&json=true","fetch_graph":"https://pith.science/api/pith-number/GOLPT2QRJQPLZIHOOBSN6C7ZLS/graph.json","fetch_events":"https://pith.science/api/pith-number/GOLPT2QRJQPLZIHOOBSN6C7ZLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOLPT2QRJQPLZIHOOBSN6C7ZLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOLPT2QRJQPLZIHOOBSN6C7ZLS/action/storage_attestation","attest_author":"https://pith.science/pith/GOLPT2QRJQPLZIHOOBSN6C7ZLS/action/author_attestation","sign_citation":"https://pith.science/pith/GOLPT2QRJQPLZIHOOBSN6C7ZLS/action/citation_signature","submit_replication":"https://pith.science/pith/GOLPT2QRJQPLZIHOOBSN6C7ZLS/action/replication_record"}},"created_at":"2026-07-05T09:43:50.701099+00:00","updated_at":"2026-07-05T09:43:50.701099+00:00"}