Learning less is more: 6D camera localization via 3D surface regression
Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization. In this work, we address the task of predicting the 6D camera pose from a single RGB image in a given 3D environment. With the advent of neural networks, previous works...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article (Journal) Chapter/Article |
| Language: | English |
| Published: |
27 Mar 2018
|
| In: |
Arxiv
|
| Online Access: | Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/1711.10228
|
| Author Notes: | Eric Brachmann and Carsten Rother |
| Summary: | Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization. In this work, we address the task of predicting the 6D camera pose from a single RGB image in a given 3D environment. With the advent of neural networks, previous works have either learned the entire camera localization process, or multiple components of a camera localization pipeline. Our key contribution is to demonstrate and explain that learning a single component of this pipeline is sufficient. This component is a fully convolutional neural network for densely regressing so-called scene coordinates, defining the correspondence between the input image and the 3D scene space. The neural network is prepended to a new end-to-end trainable pipeline. Our system is efficient, highly accurate, robust in training, and exhibits outstanding generalization capabilities. It exceeds state-of-the-art consistently on indoor and outdoor datasets. Interestingly, our approach surpasses existing techniques even without utilizing a 3D model of the scene during training, since the network is able to discover 3D scene geometry automatically, solely from single-view constraints. |
|---|---|
| Item Description: | Gesehen am 14.09.2020 |
| Physical Description: | Online Resource |