Target-Quality Image Compression with Recurrent, Convolutional Neural Networks
arXiv: Computer Vision and Pattern Recognition, Volume abs/1705.06687, 2017.
We introduce a stop-code tolerant (SCT) approach to training recurrent convolutional neural networks for lossy image compression. Our methods introduce a multi-pass training method to combine the training goals of high-quality reconstructions in areas around stop-code masking as well as in highly-detailed areas. These methods lead to lowe...More
Full Text (Upload PDF)
PPT (Upload PPT)