Deep-learning-based image compression for microscopy images: An empirical study. [PDF]
Biol ImagingWith the fast development of modern microscopes and bioimaging techniques, an unprecedentedly large amount of imaging data is being generated, stored, analyzed, and shared through networks.
Zhou Y, Sollmann J, Chen J.
europepmc +2 more sources
Three-Dimensional Adaptive Image Compression Concept for Medical Imaging: Application to Computed Tomography Angiography for Peripheral Arteries. [PDF]
J Cardiovasc Dev Dis, 2022 Advances in computed tomography (CT) have resulted in a substantial increase in the size of datasets. We built a new concept of medical image compression that provides the best compromise between compression rate and image quality. The method is based on
Fahrni G +4 more
europepmc +2 more sources
High-Quality Image Compression Algorithm Design Based on Unsupervised Learning. [PDF]
Sensors (Basel)Increasingly massive image data is restricted by conditions such as information transmission and reconstruction, and it is increasingly difficult to meet the requirements of speed and integrity in the information age.
Han S, Mo B, Zhao J, Xu J, Sun S, Jin B.
europepmc +2 more sources
Learned Image Compression with Mixed Transformer-CNN Architectures [PDF]
Computer Vision and Pattern Recognition, 2023 Learned image compression (LIC) methods have exhibited promising progress and superior rate-distortion performance compared with classical image compression standards.
Jinming Liu, Heming Sun, J. Katto
semanticscholar +1 more source
ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding [PDF]
Computer Vision and Pattern Recognition, 2022 Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promising to be large-scale adopted.
Dailan He +5 more
semanticscholar +1 more source
The Devil Is in the Details: Window-based Attention for Image Compression [PDF]
Computer Vision and Pattern Recognition, 2022 Learned image compression methods have exhibited superior rate-distortion performance than classical image compression standards. Most existing learned image compression models are based on Convolutional Neural Networks (CNNs).
Renjie Zou +2 more
semanticscholar +1 more source
Checkerboard Context Model for Efficient Learned Image Compression [PDF]
Computer Vision and Pattern Recognition, 2021 For learned image compression, the autoregressive context model is proved effective in improving the rate-distortion (RD) performance. Because it helps remove spatial redundancies among latent representations.
Dailan He +4 more
semanticscholar +1 more source
A comparative analysis of the state-of-the-art lossless image compression techniques [PDF]
SHS Web of Conferences, 2022 Lossless data reduction is essential for data transmission over the Internet and the storage of data in a digital device when data loss is not permitted. The application of image compression is essential for image storing, image classification, and image
Rahman Atiqur +2 more
doaj +1 more source
Lossy Image Compression with Conditional Diffusion Models [PDF]
Neural Information Processing Systems, 2022 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 there, mapped
Ruihan Yang, S. Mandt
semanticscholar +1 more source
Enhanced Invertible Encoding for Learned Image Compression [PDF]
ACM Multimedia, 2021 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 developments focus on
Yueqi Xie, Ka Leong Cheng, Qifeng Chen
semanticscholar +1 more source