DeepAI AI Chat
Log In Sign Up

SPP-Net: Deep Absolute Pose Regression with Synthetic Views

by   Pulak Purkait, et al.

Image based localization is one of the important problems in computer vision due to its wide applicability in robotics, augmented reality, and autonomous systems. There is a rich set of methods described in the literature how to geometrically register a 2D image w.r.t. a 3D model. Recently, methods based on deep (and convolutional) feedforward networks (CNNs) became popular for pose regression. However, these CNN-based methods are still less accurate than geometry based methods despite being fast and memory efficient. In this work we design a deep neural network architecture based on sparse feature descriptors to estimate the absolute pose of an image. Our choice of using sparse feature descriptors has two major advantages: first, our network is significantly smaller than the CNNs proposed in the literature for this task---thereby making our approach more efficient and scalable. Second---and more importantly---, usage of sparse features allows to augment the training data with synthetic viewpoints, which leads to substantial improvements in the generalization performance to unseen poses. Thus, our proposed method aims to combine the best of the two worlds---feature-based localization and CNN-based pose regression--to achieve state-of-the-art performance in the absolute pose estimation. A detailed analysis of the proposed architecture and a rigorous evaluation on the existing datasets are provided to support our method.


page 7

page 8


A Critical Analysis of Image-based Camera Pose Estimation Techniques

Camera, and associated with its objects within the field of view, locali...

A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objective

Identifying the camera pose for a given image is a challenging problem w...

Improving the generalization of network based relative pose regression: dimension reduction as a regularizer

Visual localization occupies an important position in many areas such as...

Homography Estimation with Convolutional Neural Networks Under Conditions of Variance

Planar homography estimation is foundational to many computer vision pro...

Towards Pose-invariant Lip-Reading

Lip-reading models have been significantly improved recently thanks to p...

Fast and Lightweight Scene Regressor for Camera Relocalization

Camera relocalization involving a prior 3D reconstruction plays a crucia...

Features for Ground Texture Based Localization – A Survey

Ground texture based vehicle localization using feature-based methods is...