TY - GEN
T1 - InverseNet
T2 - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019
AU - Wei, Qi
AU - Fan, Kai
AU - Wang, Wenlin
AU - Zheng, Tianhang
AU - Amit, Chakraborty
AU - Heller, Katherine
AU - Chen, Changyou
AU - Ren, Kui
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - 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.
AB - 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.
KW - Inverse problem
KW - Splitting networks
UR - https://www.scopus.com/pages/publications/85071024313
U2 - 10.1109/ICME.2019.00230
DO - 10.1109/ICME.2019.00230
M3 - Conference contribution
AN - SCOPUS:85071024313
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
SP - 1324
EP - 1329
BT - Proceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019
PB - IEEE Computer Society
Y2 - 8 July 2019 through 12 July 2019
ER -