Paper Info
Title
InverseNet: Solving Inverse Problems with Splitting Networks.
Abstract
We propose a new method that uses deep learning techniques to solve the inverse problems. The inverse problem is cast in the form of learning an end-to-end mapping from observed data to the ground-truth. Inspired by the splitting strategy widely used in regularized iterative algorithm to tackle inverse problems, the mapping is decomposed into two networks, with one handling the inversion of the physical forward model associated with the data term and one handling the denoising of the output from the former network, i.e., the inverted version, associated with the prior/regularization term. The two networks are trained jointly to learn the end-to-end mapping, getting rid of a two-step training. The training is annealing as the intermediate variable between these two networks bridges the gap between the input (the degraded version of output) and output and progressively approaches to the ground-truth. The proposed network, referred to as InverseNet, is flexible in the sense that most of the existing end-to-end network structure can be leveraged in the first network and most of the existing denoising network structure can be used in the second one. Extensive experiments on both synthetic data and real datasets on the tasks, motion deblurring, super-resolution, and colorization, demonstrate the efficiency and accuracy of the proposed method compared with other image processing algorithms.
Year
Venue
Field
2017
arXiv: Computer Vision and Pattern Recognition
Noise reduction,Deblurring,Pattern recognition,Iterative method,Computer science,Algorithm,Synthetic data,Regularization (mathematics),Inverse problem,Artificial intelligence,Deep learning,Digital image processing
DocType
Volume
Citations 
Journal
abs/1712.00202
1
PageRank 
References 
Authors
0.37
30
5
Name
Order
Citations
PageRank
Kai Fan1242.60
Qi Wei226513.31
Wenlin Wang3517.06
Amit Chakraborty423.08
Katherine A. Heller544439.41