This results in a so called rate-distortion trade-off, where a balance is found between the bitrate R and the distortion d by minimizing d + β R, where β > 0 balances the two competing objectives. While in lossless image compression the compression rate is limited by the requirement that the original image should be perfectly reconstructible, in lossy image compression, a greater reduction in storage is enabled by allowing for some distortion in the reconstructed image. Image compression refers to the task of representing images using as little storage (i.e., bits) as possible. 1 Introduction Figure 1: State-of-the-art performance achieved by our simple compression system composed of a standard convolutional auto-encoder and a 3D-CNN-based context model. Our experiments show that this approach yields a state-of-the-art image compression system based on a simple convolutional auto-encoder. The main idea is to directly model the entropy of the latent representation by using a context model: a 3D-CNN which learns a conditional probability model of the latent distribution of the auto-encoder.ĭuring training, the auto-encoder makes use of the context model to estimate the entropy of its representation, and the context model is concurrently updated to learn the dependencies between the symbols in the latent representation.
In this paper, we focus on the latter challenge and propose a new technique to navigate the rate-distortion trade-off for an image compression auto-encoder. The key challenge in learning such networks is twofold: to deal with quantization, and to control the trade-off between reconstruction error (distortion) and entropy (rate) of the latent image representation. Deep Neural Networks trained as image auto-encoders have recently emerged as a promising direction for advancing the state of the art in image compression.
0 kommentar(er)
