Does Robust VIO Need More Learning? Geometry-Verified Visual Measurements under Distribution Shift

• URL: http://arxiv.org/abs/2607.17956v1
• Date: Mon, 20 Jul 2026 13:57:44 GMT
• Title: Does Robust VIO Need More Learning? Geometry-Verified Visual Measurements under Distribution Shift
• Abstract summary: We propose a minimal-learning stereo VIO framework in which SEA-RAFT is used only to propose dense stereo correspondences and predict their uncertainty.<n>Dense flow is sampled at sparse feature locations, filtered using predicted uncertainty and stereo epipolar consistency, and incorporated into a sliding-window stereo-inertial estimator.<n>Experiments on EuRoC, VIODE, and 4Seasons demonstrate accurate and stable estimation under motion blur, dynamic scenes, illumination changes, and large indoor-to-outdoor distribution shifts.
• Score: 18.007082445726756
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Learning is increasingly introduced into visual-inertial odometry (VIO), ranging from learned feature front-ends to learning-dominant motion and geometry estimation. However, learning more of the pipeline does not necessarily improve robustness when deployment conditions differ from the training distribution. This work asks whether robust VIO under distribution shift truly requires deeper learned estimation, or whether learning can be confined to visual measurement generation. We propose a minimal-learning stereo VIO framework in which SEA-RAFT is used only to propose dense stereo correspondences and predict their uncertainty, while temporal tracking, geometric verification, and state estimation remain explicit. Dense flow is sampled at sparse feature locations, filtered using predicted uncertainty and stereo epipolar consistency, and incorporated into a sliding-window stereo-inertial estimator through uncertainty-weighted reprojection factors. The same uncertainty is further propagated through stereo triangulation for downstream anisotropic 3D Gaussian mapping. Experiments on EuRoC, VIODE, and 4Seasons demonstrate accurate and stable estimation under motion blur, dynamic scenes, illumination changes, and large indoor-to-outdoor distribution shifts. Ablations show that learned flow alone is insufficient: the gains arise from combining learned correspondence proposals with geometric verification and uncertainty-aware weighting. These results suggest that, for OOD-robust VIO, carefully integrated learned visual measurements can be more effective than learning a larger fraction of the estimation pipeline. Code and configs for the benchmark will be open-source upon acceptance. A supplementary video is available at https://drive.google.com/file/d/1EVRhOkhanmNXHbQS1Vr80FoEIAYOYOV2/view

Related papers

• TANGO-VIO: Triangulation-Aware Navigation with Guaranteed Feature-Observability for Visual-Inertial Odometry [0.0]
  This study presents TANGO-VIO, a triangulation-aware navigation framework that embeds a log-determinant metric of the feature-wise stacked-bearing matrix into a control barrier function.<n>The proposed architecture is evaluated through software-inthe- loop simulations and real flight experiments.
  arXiv  Detail & Related papers  (2026-08-03T11:32:30Z)
• MDE-VIO: Enhancing Visual-Inertial Odometry Using Learned Depth Priors [8.2208199207543]
  We propose a novel framework that enforces affine-invariant depth consistency and pairwise ordinal constraints.<n>This approach strictly adheres to the computational limits of edge devices while robustly recovering metric scale.
  arXiv  Detail & Related papers  (2026-02-11T19:53:06Z)
• GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection [92.41859045360532]
  We propose a novel Geometry Uncertainty Propagation Network (GUPNet++)<n>It models the uncertainty propagation relationship of the geometry projection during training, improving the stability and efficiency of the end-to-end model learning.<n> Experiments show that the proposed approach not only obtains (state-of-the-art) SOTA performance in image-based monocular 3D detection but also demonstrates superiority in efficacy with a simplified framework.
  arXiv  Detail & Related papers  (2023-10-24T08:45:15Z)
• Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics [74.1720528573331]
  Unsupervised monocular depth and ego-motion estimation has drawn extensive research attention in recent years. We propose DynaDepth, a novel scale-aware framework that integrates information from vision and IMU motion dynamics. We validate the effectiveness of DynaDepth by conducting extensive experiments and simulations on the KITTI and Make3D datasets.
  arXiv  Detail & Related papers  (2022-07-11T07:50:22Z)
• Emulating Spatio-Temporal Realizations of Three-Dimensional Isotropic Turbulence via Deep Sequence Learning Models [24.025975236316842]
  We use a data-driven approach to model a three-dimensional turbulent flow using cutting-edge Deep Learning techniques. The accuracy of the model is assessed using statistical and physics-based metrics.
  arXiv  Detail & Related papers  (2021-12-07T03:33:39Z)
• Unsupervised Scale-consistent Depth Learning from Video [131.3074342883371]
  We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training. Thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into the ORB-SLAM2 system. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training.
  arXiv  Detail & Related papers  (2021-05-25T02:17:56Z)
• Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction [87.08227378010874]
  We show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, we significantly improve the accuracy and robustness of monocular depth estimation. We show state-of-the-art results of learning metric depth on NYU Depth-V2 and KITTI.
  arXiv  Detail & Related papers  (2021-03-07T00:08:21Z)
• DF-VO: What Should Be Learnt for Visual Odometry? [33.379888882093965]
  We design a simple yet robust Visual Odometry system by integrating multi-view geometry and deep learning on Depth and optical Flow. Comprehensive ablation studies show the effectiveness of the proposed method, and extensive evaluation results show the state-of-the-art performance of our system.
  arXiv  Detail & Related papers  (2021-03-01T11:50:39Z)
• Learning Accurate Dense Correspondences and When to Trust Them [161.76275845530964]
  We aim to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map. We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty. Our approach obtains state-of-the-art results on challenging geometric matching and optical flow datasets.
  arXiv  Detail & Related papers  (2021-01-05T18:54:11Z)
• CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth [83.77839773394106]
  We present a lightweight, tightly-coupled deep depth network and visual-inertial odometry system. We provide the network with previously marginalized sparse features from VIO to increase the accuracy of initial depth prediction. We show that it can run in real-time with single-thread execution while utilizing GPU acceleration only for the network and code Jacobian.
  arXiv  Detail & Related papers  (2020-12-18T09:42:54Z)
• TLIO: Tight Learned Inertial Odometry [43.17991168599939]
  We propose a tightly-coupled Extended Kalman Filter framework for IMU-only state estimation. We show that our network, trained with pedestrian data from a headset, can produce statistically consistent measurement and uncertainty.
  arXiv  Detail & Related papers  (2020-07-06T03:13:34Z)
• Denoising IMU Gyroscopes with Deep Learning for Open-Loop Attitude Estimation [0.0]
  This paper proposes a learning method for denoising gyroscopes of Inertial Measurement Units (IMUs) using ground truth data. The obtained algorithm outperforms the state-of-the-art on the (unseen) test sequences.
  arXiv  Detail & Related papers  (2020-02-25T08:04:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.