Autoencoder based image compression: can the learning be quantization independent?
This paper explores the problem of learning transforms for image compression via autoencoders. Usually, the rate-distortion performances of image compression are tuned by varying the quantization step size. In the case of autoen-coders, this in principle would require learning one transform per rate-distortion point at a given quantization step size. Here, we show that comparable performances can be obtained with a unique learned transform. The different rate-distortion points are then reached by varying the quantization step size at test time. This approach saves a lot of training time.
Code (0)
등록된 구현이 없습니다.
Tasks
Image CompressionQuantizationSimilar Papers 제목 키워드 기반
QARV: Quantization-Aware ResNet VAE for Lossy Image Compression
This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications. We start by reviewing the framework of varia…
Image CompressionQuantizationVariable Rate Deep Image Compression With a Conditional Autoencoder
In this paper, we propose a novel variable-rate learned image compression framework with a conditional autoencoder. Previous learning-based image compression methods mostly require training separate networks for differen…
Image CompressionQuantizationLossy Image Compression with Quantized Hierarchical VAEs
Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory. Motivated by this, we consider the problem of lossy image compression from the perspective…
Image CompressionQuantizationVariational Bayesian Quantization
We propose a novel algorithm for quantizing continuous latent representations in trained models. Our approach applies to deep probabilistic models, such as variational autoencoders (VAEs), and enables both data and model…
Image CompressionModel CompressionQuantizationWord EmbeddingsHierarchical Quantized Autoencoders
Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and abstract features at very low bitrates. Encouraged by recent success in learning d…
Image CompressionQuantization