Image-based Localization with Spatial LSTMs.
2016
In this work we propose a new CNN+LSTM architecture for camera pose
regression for indoor and outdoor scenes. CNNs allow us to learn suitable
feature representations for localization that are robust against motion blur
and illumination changes. We make use of LSTM units on the CNN output in
spatial coordinates in order to capture contextual information. This
substantially enlarges the receptive field of each pixel leading to drastic
improvements in localization performance. We provide extensive quantitative
comparison of CNN-based vs SIFT-based localization methods, showing the
weaknesses and strengths of each. Furthermore, we present a new large-scale
indoor dataset with accurate ground truth from a laser scanner. Experimental
results on both indoor and outdoor public datasets show our method outperforms
existing deep architectures, and can localize images in hard conditions, e.g.,
in the presence of mostly textureless surfaces.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
58
References
42
Citations
NaN
KQI