pith. sign in

arxiv: 1903.07504 · v1 · pith:SWUP53NJnew · submitted 2019-03-18 · 💻 cs.CV

Understanding the Limitations of CNN-based Absolute Camera Pose Regression

classification 💻 cs.CV
keywords poseregressioncameraimagemethodsmodelaccurateapproaches
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Introduction to Camera Pose Estimation with Deep Learning

    cs.CV 2019-07 unverdicted novelty 2.0

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