Related papers: FRAPPE: Full Input, Residual Output Autoencoding w…
Neural image compression methods have seen increasingly strong performance in recent years. However, they suffer orders of magnitude higher computational complexity compared to traditional codecs, which hinders their real-world deployment.…
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…
Learned image compression has recently shown the potential to outperform the standard codecs. State-of-the-art rate-distortion (R-D) performance has been achieved by context-adaptive entropy coding approaches in which hyperprior and…
Recent advancements in deep learning-based image compression are notable. However, prevalent schemes that employ a serial context-adaptive entropy model to enhance rate-distortion (R-D) performance are markedly slow. Furthermore, the…
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…
In the fourth generation Audio Video coding Standard (AVS4), the Inter Prediction Filter (INTERPF) reduces discontinuities between prediction and adjacent reconstructed pixels in inter prediction. The paper proposes a low complexity…
For decades, video compression technology has been a prominent research area. Traditional hybrid video compression framework and end-to-end frameworks continue to explore various intra- and inter-frame reference and prediction strategies…
This paper aims to develop a new and robust approach to feature representation. Motivated by the success of Auto-Encoders, we first theoretical summarize the general properties of all algorithms that are based on traditional Auto-Encoders:…
Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents direct generation at higher resolutions. Naively transferring training-free extrapolation…
We propose a data-driven approach for deep convolutional neural network compression that achieves high accuracy with high throughput and low memory requirements. Current network compression methods either find a low-rank factorization of…
Lossy compression algorithms are typically designed to achieve the lowest possible distortion at a given bit rate. However, recent studies show that pursuing high perceptual quality would lead to increase of the lowest achievable distortion…
Energy-efficient image acquisition on the edge is crucial for enabling remote sensing applications where the sensor node has weak compute capabilities and must transmit data to a remote server/cloud for processing. To reduce the edge energy…
Research on Deep Neural Networks (DNNs) has focused on improving performance and accuracy for real-world deployments, leading to new models, such as Spiking Neural Networks (SNNs), and optimization techniques, e.g., quantization and pruning…
Recent advancements in diffusion-based generative priors have enabled visually plausible image compression at extremely low bit rates. However, existing approaches suffer from slow sampling processes and suboptimal bit allocation due to…
The substantial computational costs of diffusion models, especially due to the repeated denoising steps necessary for high-quality image generation, present a major obstacle to their widespread adoption. While several studies have attempted…
In this paper, we propose a new interactive compression scheme for omnidirectional images. This requires two characteristics: efficient compression of data, to lower the storage cost, and random access ability to extract part of the…
Feature coding for machines (FCM) is a lossy compression paradigm for split-inference. The transmitter encodes the outputs of the first part of a neural network before sending them to the receiver for completing the inference. Practical FCM…
Recently Implicit Neural Representations (INRs) gained attention as a novel and effective representation for various data types. Thus far, prior work mostly focused on optimizing their reconstruction performance. This work investigates INRs…
The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling…
In this paper, we propose an end-to-end mixed-resolution image compression framework with convolutional neural networks. Firstly, given one input image, feature description neural network (FDNN) is used to generate a new representation of…