Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimation

  title={Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimation},
  author={Haoming Chen and Tingbo Liao and Hsuan-Kung Yang and Chun-Yi Lee},
  journal={2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
This paper introduces pixel-wise prediction based visual odometry (PWVO), which is a dense prediction task that evaluates the values of translation and rotation for every pixel in its input observations. PWVO employs uncertainty estimation to identify the noisy regions in the input observations, and adopts a selection mechanism to integrate pixel-wise predictions based on the estimated uncertainty maps to derive the final translation and rotation. In order to train PWVO in a comprehensive… 

Figures and Tables from this paper



Uncertainty Estimation for Data-Driven Visual Odometry

This work proposes uncertainty-aware VO (UA-VO), a novel deep neural network (DNN) architecture that computes relative pose predictions by processing sequence of images and, at the same time, provides uncertainty measures about those estimations.

Dynamic Attention-based Visual Odometry

This paper proposes a dynamic attention-based visual odometry framework (DAVO), a learning-based VO method, for estimating the ego-motion of a monocular camera, and performs a number of experiments to examine the impacts of the dynamically adjusted weights on the accuracy of the evaluated trajectories.

Exploring Representation Learning With CNNs for Frame-to-Frame Ego-Motion Estimation

This work explores the use of convolutional neural networks to learn both the best visual features and the best estimator for the task of visual ego-motion estimation and shows that this approach is robust with respect to blur, luminance, and contrast anomalies and outperforms most state-of-the-art approaches even in nominal conditions.

Evaluation of non-geometric methods for visual odometry

Modelling uncertainty in deep learning for camera relocalization

  • Alex KendallR. Cipolla
  • Computer Science
    2016 IEEE International Conference on Robotics and Automation (ICRA)
  • 2016
A Bayesian convolutional neural network is used to regress the 6-DOF camera pose from a single RGB image and an estimate of the model's relocalization uncertainty is obtained to improve state of the art localization accuracy on a large scale outdoor dataset.

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

D3VO tightly incorporates the predicted depth, pose and uncertainty into a direct visual odometry method to boost both the front-end tracking as well as the back-end non-linear optimization.

TartanAir: A Dataset to Push the Limits of Visual SLAM

The goal is to push the limits of Visual SLAM algorithms in the real world by providing a challenging benchmark for testing new methods, while also using a large diverse training data for learning-based methods.

Image-Based Localization Using Hourglass Networks

An encoder-decoder convolutional neural network architecture for estimating camera pose (orientation and location) from a single RGB-image with clear improvement over the previous state-of-the-art even when compared to methods that utilize sequence of test frames instead of a single frame.

Image-Based Localization Using LSTMs for Structured Feature Correlation

Experimental results show the proposed CNN+LSTM architecture for camera pose regression for indoor and outdoor scenes outperforms existing deep architectures, and can localize images in hard conditions, where classic SIFT-based methods fail.

Geometry-Aware Learning of Maps for Camera Localization

This work proposes to represent maps as a deep neural net called MapNet, which enables learning a data-driven map representation and proposes a novel parameterization for camera rotation which is better suited for deep-learning based camera pose regression.