{"paper":{"title":"DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Diffusion priors and active view sampling let Gaussian Splatting Wang Tiles be built from minimal observations while preserving quality.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyun Wei, Jiekai Wu, Rong Fu, Simon Fong, Wangyu Wu, Xiaowen Ma, Yang Li, Yee Tan Jia","submitted_at":"2026-02-17T04:47:39Z","abstract_excerpt":"The emergence of 3D Gaussian Splatting has fundamentally redefined the capabilities of photorealistic neural rendering by enabling high-throughput synthesis of complex environments. While procedural methods like Wang Tiles have recently been integrated to facilitate the generation of expansive landscapes, these systems typically remain constrained by a reliance on densely sampled exemplar reconstructions. We present DAV-GSWT, a data-efficient framework that leverages diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal input observati"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our system significantly reduces the required data volume while maintaining the visual integrity and interactive performance necessary for large-scale virtual environments","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That diffusion models can reliably hallucinate missing structural details in a way that produces seamless tile transitions without visible artifacts or inconsistencies across boundaries.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DAV-GSWT uses diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal observations while preserving visual quality and tile transitions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Diffusion priors and active view sampling let Gaussian Splatting Wang Tiles be built from minimal observations while preserving quality.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"967c0793db875102631b2124b5aaed15428b3d3aa1390d12926cabf4e453a039"},"source":{"id":"2602.15355","kind":"arxiv","version":4},"verdict":{"id":"c62001e2-a5a3-4ecd-8095-7bedd8b14c5e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T22:04:31.171210Z","strongest_claim":"our system significantly reduces the required data volume while maintaining the visual integrity and interactive performance necessary for large-scale virtual environments","one_line_summary":"DAV-GSWT uses diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal observations while preserving visual quality and tile transitions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That diffusion models can reliably hallucinate missing structural details in a way that produces seamless tile transitions without visible artifacts or inconsistencies across boundaries.","pith_extraction_headline":"Diffusion priors and active view sampling let Gaussian Splatting Wang Tiles be built from minimal observations while preserving quality."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.15355/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"}