{"paper":{"title":"GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GSCompleter completes sparse-view 3D Gaussian Splatting scenes in seconds by lifting synthesized 2D references into metric 3D primitives.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ao Gao, Jingyu Gong, Lizhuang Ma, Xin Tan, Yuan Xie, Zhizhong Zhang","submitted_at":"2026-04-22T03:47:25Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has revolutionized high-fidelity neural rendering with its explicit representation and efficiency. However, reconstructing scenes from sparse viewpoints suffers from severe geometric voids and floaters due to limited coverage. Current scene completion methods typically rely on an iterative \"Repair-then-Distill\" paradigm, which is computationally intensive, prone to unstable optimization, and susceptible to overfitting. To address these limitations, we propose GSCompleter, a distillation-free plugin that shifts scene completion to a stable \"Generate-then-Register\" w"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This shift to a rapid registration paradigm delivers superior 3DGS completion performance across three distinct benchmarks, enhancing the quality and efficiency of various baselines and achieving new SOTA results.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The synthesized 2D reference images are sufficiently plausible and geometrically consistent to be lifted into accurate metric-scale 3D primitives via the Stereo-Anchor mechanism without introducing new artifacts or scale errors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GSCompleter completes sparse 3D Gaussian Splatting scenes via a distillation-free generate-then-register pipeline using Stereo-Anchor lifting and Ray-Constrained Registration, delivering SOTA results on three benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GSCompleter completes sparse-view 3D Gaussian Splatting scenes in seconds by lifting synthesized 2D references into metric 3D primitives.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"820ee80e28d0ca2be2f1650de03cd375089e9e84171a91d4ba4c01f9ab77e94a"},"source":{"id":"2604.20155","kind":"arxiv","version":2},"verdict":{"id":"8a0a2c1f-6785-48cf-a065-2705f630ce77","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T01:18:10.007516Z","strongest_claim":"This shift to a rapid registration paradigm delivers superior 3DGS completion performance across three distinct benchmarks, enhancing the quality and efficiency of various baselines and achieving new SOTA results.","one_line_summary":"GSCompleter completes sparse 3D Gaussian Splatting scenes via a distillation-free generate-then-register pipeline using Stereo-Anchor lifting and Ray-Constrained Registration, delivering SOTA results on three benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The synthesized 2D reference images are sufficiently plausible and geometrically consistent to be lifted into accurate metric-scale 3D primitives via the Stereo-Anchor mechanism without introducing new artifacts or scale errors.","pith_extraction_headline":"GSCompleter completes sparse-view 3D Gaussian Splatting scenes in seconds by lifting synthesized 2D references into metric 3D primitives."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.20155/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"}