Target-Quality Image Compression with Recurrent, Convolutional Neural Networks
This work addresses image compression for applications requiring high-quality reconstructions, representing an incremental improvement over existing neural network methods.
The paper tackles lossy image compression by introducing a stop-code tolerant (SCT) approach with recurrent convolutional neural networks, achieving lower bitrates and maintaining or exceeding image quality compared to JPEG and RNN auto-encoders on the Kodak dataset.
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 lower true bitrates for a given recursion count, both pre- and post-entropy coding, even using unstructured LZ77 code compression. The pre-LZ77 gains are achieved by trimming stop codes. The post-LZ77 gains are due to the highly unequal distributions of 0/1 codes from the SCT architectures. With these code compressions, the SCT architecture maintains or exceeds the image quality at all compression rates compared to JPEG and to RNN auto-encoders across the Kodak dataset. In addition, the SCT coding results in lower variance in image quality across the extent of the image, a characteristic that has been shown to be important in human ratings of image quality