{"paper":{"title":"GeoGS-CE: Learning Delay--Beam Channel Priors with 3D Gaussians for High-Mobility Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A 3D Gaussian model of scene geometry supplies a stable delay-beam prior that reconstructs full channel responses from sparse pilots in high-mobility settings.","cross_cats":["cs.AI","math.IT"],"primary_cat":"cs.IT","authors_text":"Chaozheng Wen, Chenghong Bian, Jiajia Guo, Jun Zhang, Yumeng Zhang","submitted_at":"2026-05-15T15:49:42Z","abstract_excerpt":"Wideband channel estimation (CE) in high-mobility scenarios remains challenging because channel responses vary rapidly, while practical systems can allocate only sparse pilots to accommodate dense users. Fortunately, many high-mobility environments, such as high-speed railways, exhibit scheduled trajectories, predictable velocities, and a limited number of dominant propagation paths. These properties induce a delay--beam power spectrum that is more stable than the instantaneous complex channel frequency response (CFR), less sensitive to the random phase coherence, and rich in geometric informa"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The geometric prior substantially improves CFR reconstruction over pilot-only and non-geometric baselines in simulations based on channels generated from a segment of the Guangshen high-speed railway.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"High-mobility environments such as high-speed railways exhibit scheduled trajectories, predictable velocities, and a limited number of dominant propagation paths that induce a delay-beam power spectrum more stable than the instantaneous CFR.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GeoGS-CE models NLoS scattering with 3D Gaussians and uses differentiable rendering to generate delay-beam power spectrum priors that improve full CFR reconstruction via MMSE in sparse-pilot high-mobility settings.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A 3D Gaussian model of scene geometry supplies a stable delay-beam prior that reconstructs full channel responses from sparse pilots in high-mobility settings.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b7750e2ebdc6c88b990014125455e4e01ac97ba3f5f383cf5c80c3cfc9660b09"},"source":{"id":"2605.16094","kind":"arxiv","version":1},"verdict":{"id":"b2be8291-e32c-4a98-9eee-93969f43d21b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T19:06:22.161263Z","strongest_claim":"The geometric prior substantially improves CFR reconstruction over pilot-only and non-geometric baselines in simulations based on channels generated from a segment of the Guangshen high-speed railway.","one_line_summary":"GeoGS-CE models NLoS scattering with 3D Gaussians and uses differentiable rendering to generate delay-beam power spectrum priors that improve full CFR reconstruction via MMSE in sparse-pilot high-mobility settings.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"High-mobility environments such as high-speed railways exhibit scheduled trajectories, predictable velocities, and a limited number of dominant propagation paths that induce a delay-beam power spectrum more stable than the instantaneous CFR.","pith_extraction_headline":"A 3D Gaussian model of scene geometry supplies a stable delay-beam prior that reconstructs full channel responses from sparse pilots in high-mobility settings."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16094/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T19:31:18.993973Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T19:20:51.118373Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:38.862742Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.494009Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e5b00e46188d8f9e6d22b828b1b54243e2c766614204c303227399729b9ed78f"},"references":{"count":24,"sample":[{"doi":"","year":2015,"title":"T. Zhou, C. Tao, S. Salous, L. Liu, and Z. Tan, `` Channel sounding for high-speed railway communication systems ,'' IEEE Communications Magazine, vol. 53, no. 10, pp. 70--77, 2015","work_id":"43f78616-79f2-4970-813f-c94fa16185dd","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1915,"title":"C. Wu, X. Yi, Y. Zhu, W. Wang, L. You, and X. Gao, `` Channel prediction in high-mobility massive MIMO: From spatio-temporal autoregression to deep learning ,'' IEEE Journal on Selected Areas in Commu","work_id":"b8bffcce-244a-4a91-8434-7d100fc3ed28","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"W. Khawaja, I. Guvenc, and D. Matolak, `` UWB channel sounding and modeling for UAV air-to-ground propagation channels ,'' in 2016 IEEE global communications conference (GLOBECOM). 1em plus 0.5em minu","work_id":"4000802f-cfdd-447a-875f-bc448ed30220","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Y. Wan and A. Liu, `` A two-stage 2D channel extrapolation scheme for TDD 5G NR systems ,'' IEEE Transactions on Wireless Communications, vol. 23, no. 8, pp. 8497--8511, 2024","work_id":"e81f50e1-7313-4f80-9e12-7a0c6b995902","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Y. Zhang, H. Guo, and V. K. N. Lau, `` A Novel Pilot Scheme for Uplink Channel Estimation for Sub–array Structured ELAA in XL–MIMO systems ,'' IEEE Transactions on Signal Processing, pp. 1--16, 2026","work_id":"2525fd1e-a4e9-485e-940b-c2f02fba31f8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":24,"snapshot_sha256":"6ae6be945be64ccd5653132d59a9eff8efc9d87b635b06196d1b4eae2eab9998","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"f28fbea3f21bd4105e4258636e00567dab42e8ab5a7f6983256ed047ff21911b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}