{"slug": "mirage-metric-inference-and-reliability-aware-gaussian-estimation-from-feed", "title": "MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision", "summary": "Researchers introduced MIRAGE, a method that anchors feed-forward visual geometry to LiDAR–IMU metric motion and regulates online pose corrections according to correspondence support and cross-modal agreement, jointly enabling accurate metric pose estimation and high-fidelity Gaussian reconstruction. Experiments on Oxford Spires, M2DGR and INS show MIRAGE achieves accurate metric trajectory estimation, outperforming COLMAP, a widely used but computationally expensive reference for vision-only benchmarks. The team also built a multimodal data-collection platform and used MIRAGE to establish accurate 6-DoF reference trajectories for a new vision-only benchmark, on which they benchmark recent monocular large-scale reconstruction methods for long-horizon indoor scenes.", "body_md": "arXiv:2610.12568v1 Announce Type: new \nAbstract: Feed-forward 3D priors enable high-quality reconstruction from image streams but often lack reliable metric scale and suffer from long-term trajectory drift. In contrast, LiDAR--inertial estimation provides metrically accurate motion but lacks the image-space consistency needed for high-fidelity reconstruction. We propose $MIRAGE$, which anchors feed-forward visual geometry to LiDAR--IMU metric motion and regulates online pose corrections according to correspondence support and cross-modal agreement, jointly enabling accurate metric pose estimation and high-fidelity Gaussian reconstruction. Experiments on Oxford Spires, M2DGR and INS show that MIRAGE achieves accurate metric trajectory estimation, outperforming COLMAP, a widely used but computationally expensive reference for vision-only benchmarks. Motivated by the scarcity of long-horizon monocular benchmarks for large-scale indoor reconstruction, we further build a multimodal data-collection platform and use MIRAGE to establish accurate 6-DoF reference trajectories for a new vision-only benchmark. We benchmark recent monocular large-scale reconstruction methods on this dataset, providing a systematic evaluation of their performance in long-horizon indoor scenes.", "url": "https://wpnews.pro/news/mirage-metric-inference-and-reliability-aware-gaussian-estimation-from-feed", "canonical_source": "https://arxiv.org/abs/2610.12568", "published_at": "2026-10-12 04:00:00+00:00", "updated_at": "2026-10-12 04:42:28.973200+00:00", "lang": "en", "topics": ["computer-vision", "robotics", "ai-research", "machine-learning"], "entities": ["MIRAGE", "COLMAP", "Oxford Spires", "M2DGR", "INS", "LiDAR", "IMU"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/mirage-metric-inference-and-reliability-aware-gaussian-estimation-from-feed", "markdown": "https://wpnews.pro/news/mirage-metric-inference-and-reliability-aware-gaussian-estimation-from-feed.md", "text": "https://wpnews.pro/news/mirage-metric-inference-and-reliability-aware-gaussian-estimation-from-feed.txt", "jsonld": "https://wpnews.pro/news/mirage-metric-inference-and-reliability-aware-gaussian-estimation-from-feed.jsonld"}}