{"ID":6497744,"CreatedAt":"2026-07-13T01:19:40.13847098Z","UpdatedAt":"2026-07-14T01:36:59.12045529Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.09260","arxiv_id":"2607.09260","title":"AnythingReality: Robust Online Gaussian Splatting SLAM for Open-Vocabulary VR Scene Exploration","abstract":"We present a novel integrated architecture for robust online 3D Gaussian splatting, real-time VR exploration, and speech-driven Vision-Language-Model interaction. Unlike methods assuming clean depth or external poses, our system combines ORB-SLAM3-based pose estimation with online Gaussian reconstruction for noisy real-world data. A VR pipeline enables immersive exploration of incremental reconstructions; a semantic module transcribes voice commands, generates scene descriptions, and records points of interest. Against state-of-the-art online Gaussian splatting methods, we improve image quality on our dataset (+14.5% PSNR, +8.6% SSIM, -14.3% LPIPS) and TUM-RGBD (+11.7% PSNR, +7.8% SSIM, -21.6% LPIPS), with comparable or superior frame rates via quality-speed configurations. We achieve an 88% VLM object-recognition rate.","short_abstract":"We present a novel integrated architecture for robust online 3D Gaussian splatting, real-time VR exploration, and speech-driven Vision-Language-Model interaction. Unlike methods assuming clean depth or external poses, our system combines ORB-SLAM3-based pose estimation with online Gaussian reconstruction for noisy real...","url_abs":"https://arxiv.org/abs/2607.09260","url_pdf":"https://arxiv.org/pdf/2607.09260v1","authors":"[\"Timofei Kozlov\",\"Dmitrii Maliukov\",\"Andrey Marchenko\",\"Miguel Altamirano Cabrera\",\"Dzmitry Tsetserukou\"]","published":"2026-07-10T10:21:23Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"LoRA\"]","has_code":false}