pith. sign in

Understanding the Limitations of CNN-based Absolute Camera Pose Regression

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Visual localization is the task of accurate camera pose estimation in a known scene. It is a key problem in computer vision and robotics, with applications including self-driving cars, Structure-from-Motion, SLAM, and Mixed Reality. Traditionally, the localization problem has been tackled using 3D geometry. Recently, end-to-end approaches based on convolutional neural networks have become popular. These methods learn to directly regress the camera pose from an input image. However, they do not achieve the same level of pose accuracy as 3D structure-based methods. To understand this behavior, we develop a theoretical model for camera pose regression. We use our model to predict failure cases for pose regression techniques and verify our predictions through experiments. We furthermore use our model to show that pose regression is more closely related to pose approximation via image retrieval than to accurate pose estimation via 3D structure. A key result is that current approaches do not consistently outperform a handcrafted image retrieval baseline. This clearly shows that additional research is needed before pose regression algorithms are ready to compete with structure-based methods.

fields

cs.CV 1

years

2019 1

verdicts

UNVERDICTED 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • Introduction to Camera Pose Estimation with Deep Learning cs.CV · 2019-07-08 · unverdicted · none · ref 27 · internal anchor

    A survey of deep learning approaches for regressing absolute camera pose from single RGB images, covering key methods, trends, cross-comparisons, and reproducibility notes.