MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision

Key points

• Feed-forward 3D priors enable high-quality reconstruction from image streams but often lack reliable metric scale and suffer from long-term trajectory drift.1
• In contrast, LiDAR--inertial estimation provides metrically accurate motion but lacks the image-space consistency needed for high-fidelity reconstruction.1
• 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.1
• 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.1

Sources (1)

• [1]MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 06:00 PM

  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.

  Feed-forward 3D priors enable high-quality reconstruction from image streams but often lack reliable metric scale and suffer from long-term trajectory drift.

Extractive summary: sentences quoted from the sources.