cs.CVOct 30, 2026

Queryable Gaussian View Index: Text Retrieval and Selective Camera Localization

Authors: Tianyu Xiong, Rui Li, Jiaqi Yang

Organizations: School of Computer Science, Northwestern Polytechnical University Xi’an, China · CEMSE, King Abdullah University of Science and Technology Thuwal, Saudi Arabia

Abstract

We present Queryable Gaussian View Index (QGVI) for querying existing Gaussian scene assets and their associated calibrated reference data. Text-view retrieval and selective RGB camera localization return poses in the asset's coordinate frame. QGVI-T turns Gaussian-rendered views into a language-searchable index of scene locations, binding structured captions to known camera poses and place identifiers. Semantic and lexical retrieval select views from distinct places without online rendering, VLM calls, or a scene-specific pose network. The image route, QGVI-I, filters LoGS-based geometric estimates using distinct inlier query keypoints. It omits photometric refinement and preserves accepted pose coordinates. On nine development scenes, QGVI-T achieves 58.3% Top-1 and 78.3% Top-5 joint relevance-and-validity success, compared with 26.1% and 34.6% for our CityLoC reimplementation with refinement. QGVI-I achieves 97.3% scene-mean pose success at 1 m/2 degrees, with pooled false-acceptance and false-rejection rates of 0.707% and 1.142%. A paired cached evaluation retains all 1,775 initializer poses correct at this threshold. Recorded median text query latency is 0.020 s. Matched controls show competitive BM25 retrieval and slightly lower false acceptance for thresholded full LoGS; grid augmentation suggests modest gains on novel-view-derived descriptions. We report model-judged semantic success separately from source-camera recovery, with source-verified or estimated scales for geometric evaluation.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels

    Aug 31, 2026Jirong Li, Satoshi Ikehata, Shuhei Kurita +13D Gaussian SplattingCamera Pose Estimation

  2. GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations

    Aug 25, 2025Fadi Khatib, Dror Moran, Guy Trostianetsky +3Visual Place RecognitionCamera Pose Estimation