Authors:
Monika Kwiatkowski
and
Olaf Hellwich
Affiliation:
Computer Vision & Remote Sensing, Technische Universität Berlin, Marchstr. 23, Berlin, Germany
Keyword(s):
Deep Sets, Deep Learning, Image Reconstruction, Background Reconstruction, Artifact Removal.
Abstract:
When taking images of planar objects, the images are often subject to unwanted artifacts such as specularities, shadows, and occlusions. While there are some methods that specialize in the removal of each type of artifact individually, we offer a generalized solution. We implement an end-to-end deep learning approach that removes artifacts from a series of images using a fully convolutional residual architecture and Deep Sets. Our architecture can be used as general approach for many image restoration tasks and is robust to varying sequence lengths and varying image resolutions. Furthermore, it enforces permutation invariance on the input sequence. The architecture is optimized to process high resolution images. We also provide a simple online algorithm that allows the processing of arbitrarily long image sequences without increasing the memory consumption. We created a synthetic dataset as an initial proof-of-concept. Additionally, we created a smaller dataset of real image sequence
s. In order to overcome the data scarcity of our real dataset, we use the synthetic data for pre-training our model. Our evaluations show that our model outperforms many state of the art methods that are used in related problems such as background subtraction and intrinsic image decomposition.
(More)