REV-AE: A Learned Frame Set for Image Reconstruction
Lists
Only you see this
Abstract
Reversible residual network naturally extends the linear lifting scheme with no theoretic guarantee. In this paper, we propose a reversible autoencoder (Rev-AE) with this extended non-linear lifting scheme to improve image reconstruction. Nonlinear prediction and update operators are designed based on shallow convolutional neural networks to model multilayer non-linearities. Different from existing autoencoders, Rev-AE support efficient image reconstruction with parameters reusable for the symmetric encoder and decoder. Rev-AE forms a set of related frames to guarantee perfect reconstruction with the non-linear extension of classic lifting scheme. Lower and upper bounds are developed for the set of frames to relate with the singular values for each non-linear operator. Furthermore, we employ Rev-AE into lossy image compression to evaluate its effectiveness on image reconstruction. Experimental results show that Rev-AE achieves competitive performance in comparison to the state-of-the-art.
BibTeX
@inproceedings{li2020rev,
author = {Shaohui Li and Ziyang Zheng and Wenrui Dai and Junni Zou and Hongkai Xiong},
title = {{REV-AE: A Learned Frame Set for Image Reconstruction}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2020},
doi = {10.1109/icassp40776.2020.9053434},
}Loading related content...