Related papers: Joint Autoregressive and Hierarchical Priors for L…

This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an image is mapped into a latent space for entropy coding and, from…

Although deep learning based image compression methods have achieved promising progress these days, the performance of these methods still cannot match the latest compression standard Versatile Video Coding (VVC). Most of the recent…

Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D…

Autoregressive models are a class of exact inference approaches with highly flexible functional forms, yielding state-of-the-art density estimates for natural images. Yet, the sequential ordering on the dimensions makes these models…

Image compression has been investigated for many decades. Recently, deep learning approaches have achieved a great success in many computer vision tasks, and are gradually used in image compression. In this paper, we develop three overall…

JPEG images can be further compressed to enhance the storage and transmission of large-scale image datasets. Existing learned lossless compressors for RGB images cannot be well transferred to JPEG images due to the distinguishing…

Recently, there has been much interest in deep learning techniques to do image compression and there have been claims that several of these produce better results than engineered compression schemes (such as JPEG, JPEG2000 or BPG). A…

Recently, learned video compression has drawn lots of attention and show a rapid development trend with promising results. However, the previous works still suffer from some criticial issues and have a performance gap with traditional…

As a commonly-used image compression format, JPEG has been broadly applied in the transmission and storage of images. To further reduce the compression cost while maintaining the quality of JPEG images, lossless transcoding technology has…

Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency. Efficient temporal information representation plays a key role in video coding. Thus, in this paper, we propose to exploit…

We propose a novel joint lossy image and residual compression framework for learning $\ell_\infty$-constrained near-lossless image compression. Specifically, we obtain a lossy reconstruction of the raw image through lossy image compression…

Several deep learned lossy compression techniques have been proposed in the recent literature. Most of these are optimized by using either MS-SSIM (multi-scale structural similarity) or MSE (mean squared error) as a loss function.…

This paper explores learned image compression based on traditional and learned discrete wavelet transform (DWT) architectures and learned entropy models for coding DWT subband coefficients. A learned DWT is obtained through the lifting…

JPEG is one of the most popular image compression methods. It is beneficial to compress those existing JPEG files without introducing additional distortion. In this paper, we propose a deep learning based method to further compress JPEG…

A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently generative and distributive, conflicting with contrastive…

Compressed sensing is an image reconstruction technique to achieve high-quality results from limited amount of data. In order to achieve this, it utilizes prior knowledge about the samples that shall be reconstructed. Focusing on image…

We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial…

Lossy image compression is generally formulated as a joint rate-distortion optimization to learn encoder, quantizer, and decoder. However, the quantizer is non-differentiable, and discrete entropy estimation usually is required for rate…

Incremental learning aims to enable machine learning models to continuously acquire new knowledge given new classes, while maintaining the knowledge already learned for old classes. Saving a subset of training samples of previously seen…

Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised…