InverseNet: Solving Inverse Problems of Multimedia Data with Splitting Networks
Lists
Only you see this
Abstract
We propose a novel network architecture, namely InverseNet, to solve the inverse problems of multimedia data. The inverse problem is cast in the form of learning an end-to-end mapping from observed multimedia data to the ground-truth data. Inspired by the splitting strategy to tackle inverse problems, the mapping is learned by InverseNet, a composition of two networks, with one handling the inversion of the physical forward model and the other handling the denoising of the output from the former network. Training InverseNet is annealing as the intermediate variable between these two networks bridges the gap between the input and output and progressively approaches to the ground-truth. Extensive experiments on synthetic and real multimedia datasets on the tasks, e.g., motion deblurring, super-resolution, and colorization, demonstrate the efficiency and accuracy of the proposed method compared with other image processing algorithms.
BibTeX
@inproceedings{wei2019inversenet,
author = {Qi Wei and Kai Fan and Wenlin Wang and Tianhang Zheng and Amit Chakraborty and Katherine A. Heller and Changyou Chen and Kui Ren},
title = {{InverseNet: Solving Inverse Problems of Multimedia Data with Splitting Networks}},
booktitle = {ICME},
year = {2019},
doi = {10.1109/icme.2019.00230},
}Loading related content...