cs.CVNov 9, 2026

Scale-Consistent Monocular Fisheye Visual Odometry via Spherical Bundle Adjustment-Guided Unsupervised Depth Learning

Authors: Wanhui Luo, Hongbo Zhao, Yi Zhou, Qijun Chen, Yiming Nie, Rui Fan

Organizations: Department of Control Science & Engineering, the College of Electronic & Information Engineering, Tongji University, Shanghai 201804, China · Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai 201210, China · School of Artificial Intelligence and Robotics, Hunan University, 410082, Changsha, China · Unmanned Systems Technology Research Center, Defense Innovation Institute, Academy of Military Science, Beijing 100071, China · 

Abstract

The wide field of view of fisheye cameras and the simplicity of a monocular setup make monocular fisheye visual odometry (VO) attractive for robotic localization and mapping. Nevertheless, scale drift remains a major challenge over long trajectories. Unsupervised depth learning can help to mitigate this issue, but the pronounced distortion of fisheye images poses challenges for accurate depth estimation. This article presents S2^2D-FVO, a monocular fisheye VO framework integrating spherical bundle adjustment (SBA)-guided unsupervised depth learning to improve scale consistency and depth estimation accuracy. Given that pixel reprojection residuals do not uniformly reflect angular deviations between viewing rays and that the first-order linearization of a scalar angular reprojection residual is insensitive to perturbations along one tangent direction, SBA employs tangent-space angular reprojection residuals derived from the spherical logarithmic map. These residuals retain sensitivity along both tangent directions, with their norms equal to the corresponding scalar angular residuals. A median depth-based scale regularization term is further integrated into SBA to constrain the reconstruction scale. Building on these formulations, SBA replaces the pose estimation network during unsupervised depth learning, providing more reliable relative poses for view synthesis. In turn, depth estimates from the well-trained depth estimation network provide scale references for SBA, improving scale consistency while allowing individual 3-D landmark positions to be refined. Extensive experiments conducted on multiple public datasets, as well as two newly collected large-scale datasets, demonstrate that the proposed framework outperforms representative existing approaches in both depth and trajectory estimation accuracy and is applicable to different camera models.

Figures & tables

Explore similar work

CardsList
  1. Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens

    Aug 6, 2025Rit Gangopadhyay, Jung-Hee Kim, Xien Chen +3Domain AdaptationDepth Estimation

  2. SFVO: Decoupled Confidence-Guided Stereo-Flow Visual Odometry with Bidirectional PnP

    Sep 18, 2026Kai Zhang, Guoyang Zhao, Jun MaVisual OdometryCamera Pose Estimation

  3. WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimation

    May 22, 2026Ilia Indyk, Ignat Penshin, Ivan Sosin +3Metric Depth EstimationDepth Estimation