In this paper, we propose an encoder-decoder convolutional neural network (CNN) architecture for estimating camera pose (orientation and location) from a single RGBimage. The architecture has a hourglass shape consisting of a chain of convolution and up-convolution layers followed by a regression part. The up-convolution layers are introduced to preserve the fine-grained information of the input image. Following the common practice, we train our model in end-to-end manner utilizing transfer

more »

... ning from large scale classification data. The experiments demonstrate the performance of the approach on data exhibiting different lighting conditions, reflections, and motion blur. The results indicate a clear improvement over the previous state-of-theart even when compared to methods that utilize sequence of test frames instead of a single frame.