Related papers: A Cross Channel Context Model for Latents in Deep …

Convolutional neural networks (CNNs) have become increasingly difficult to deploy in resource-constrained environments due to their large memory and computational requirements. Although low-rank compression methods can reduce this burden,…

Deep network-based image Compressed Sensing (CS) has attracted much attention in recent years. However, the existing deep network-based CS schemes either reconstruct the target image in a block-by-block manner that leads to serious block…

Most existing approaches for image and video compression perform transform coding in the pixel space to reduce redundancy. However, due to the misalignment between the pixel-space distortion and human perception, such schemes often face the…

Motivated by recent work on deep neural network (DNN)-based image compression methods showing potential improvements in image quality, savings in storage, and bandwidth reduction, we propose to perform image understanding tasks such as…

Recently deep learning-based image compression methods have achieved significant achievements and gradually outperformed traditional approaches including the latest standard Versatile Video Coding (VVC) in both PSNR and MS-SSIM metrics. Two…

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 different compression rates…

Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information. In this paper, taking advantage of both classical architecture in the conventional…

We describe an end-to-end trainable model for image compression based on variational autoencoders. The model incorporates a hyperprior to effectively capture spatial dependencies in the latent representation. This hyperprior relates to side…

End-to-end deep trainable models are about to exceed the performance of the traditional handcrafted compression techniques on videos and images. The core idea is to learn a non-linear transformation, modeled as a deep neural network,…

Million-level token inputs in long-context tasks pose significant computational and memory challenges for Large Language Models (LLMs). Recently, DeepSeek-OCR conducted research into the feasibility of Contexts Optical Compression and…

Recently, vision model pre-training has evolved from relying on manually annotated datasets to leveraging large-scale, web-crawled image-text data. Despite these advances, there is no pre-training method that effectively exploits the…

The transformer structure employed in large language models (LLMs), as a specialized category of deep neural networks (DNNs) featuring attention mechanisms, stands out for their ability to identify and highlight the most relevant aspects of…

Recently, learned video compression has achieved exciting performance. Following the traditional hybrid prediction coding framework, most learned methods generally adopt the motion estimation motion compensation (MEMC) method to remove…

Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high-quality reconstructions, they are typically complex, heavyweight, and require substantial…

Context-aware compression techniques have gained increasing attention as model sizes continue to grow, introducing computational bottlenecks that hinder efficient deployment. A structured encoding approach was proposed to selectively…

In recent years, learned image compression methods have demonstrated superior rate-distortion performance compared to traditional image compression methods. Recent methods utilize convolutional neural networks (CNN), variational…

This paper studies cross-domain lossy compression through the lens of minimum entropy coupling (MEC) with rate and classification constraints. In this setting, an encoder observes samples from a degraded source domain, while the decoder is…

DeepSeek-OCR shows that rendered text can be reconstructed from a small number of vision tokens, sparking excitement about using vision as a compression medium for long textual contexts. But this pipeline requires rendering token embeddings…

Diffusion models have achieved remarkable success in generating high quality image and video data. More recently, they have also been used for image compression with high perceptual quality. In this paper, we present a novel approach to…

Existing compression methods typically focus on the removal of signal-level redundancies, while the potential and versatility of decomposing visual data into compact conceptual components still lack further study. To this end, we propose a…