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

Computer Science > Computer Vision and Pattern Recognition arXiv:2610.12568 (cs) [Submitted on 8 Oct 2026] Title: MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision Authors: Xinzhe Wang, Changjian Jiang, Kaiwen Song, Xudong Li, Kerui Ren, Ran Yi, Lizhuang Ma, Chunhua Shen, Linning Xu, Tao Lu, Mulin Yu.

计算机科学 > 计算机视觉与模式识别 arXiv:2610.12568 (cs) [提交于 2026 年 10 月 8 日] 标题：MIRAGE：基于前馈视觉的度量推理与可靠性感知高斯估计。作者：Xinzhe Wang, Changjian Jiang, Kaiwen Song, Xudong Li, Kerui Ren, Ran Yi, Lizhuang Ma, Chunhua Shen, Linning Xu, Tao Lu, Mulin Yu。

Abstract: 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.

摘要：前馈 3D 先验能够实现从图像流中进行高质量重建，但往往缺乏可靠的度量尺度，且容易受到长期轨迹漂移的影响。相比之下，激光雷达-惯性估计提供了度量精确的运动，但缺乏高保真重建所需的图像空间一致性。我们提出了 $MIRAGE$，它将前馈视觉几何与激光雷达-惯性测量单元（LiDAR-IMU）的度量运动相结合，并根据对应关系支持和跨模态一致性来调节在线位姿校正，从而共同实现了精确的度量位姿估计和高保真高斯重建。

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.

在 Oxford Spires、M2DGR 和 INS 上的实验表明，MIRAGE 实现了精确的度量轨迹估计，性能优于 COLMAP（一种广泛使用但计算成本高昂的纯视觉基准参考工具）。受限于大规模室内重建缺乏长视距单目基准的现状，我们进一步构建了一个多模态数据采集平台，并利用 MIRAGE 为一个新的纯视觉基准建立了精确的 6-DoF 参考轨迹。我们在该数据集上对近期的单目大规模重建方法进行了基准测试，为它们在长视距室内场景中的表现提供了系统性评估。