Results 61 to 70 of about 411 (87)
Unveiling the Future of Human and Machine Coding: A Survey of End-to-End Learned Image Compression. [PDF]
Entropy (Basel)Huang CH, Wu JL.
europepmc +1 more source
Deep Learning-Based Image Steganography with Latent Space Embedding and Smart Decoder Selection. [PDF]
Entropy (Basel)Zhou Y, Wang N, Hong X, Peng Y, Shao S.
europepmc +1 more source
Hybrid deep learning architecture for scalable and high-quality image compression. [PDF]
Sci RepAl-Khafaji M, Ramaha NTA.
europepmc +1 more source
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Unified Lossy and Near-Lossless Hyperspectral Image Compression Based on JPEG 2000
IEEE Geoscience and Remote Sensing Letters, 2008We propose a compression algorithm for hyperspectral images featuring both lossy and near-lossless compression. The algorithm is based on JPEG 2000 and provides better near-lossless compression performance than 3D-CALIC. We also show that its effect on the results of selected applications is negligible and, in some cases, better than JPEG 2000.
G. CARVAJAL +2 more
openaire +4 more sources
Atomic wavelets in lossy and near-lossless image compression
Image and Signal Processing for Remote Sensing XXVI, 2020One of distinguishing features of the present is the explosive increase in data amount including digital images such as satellite remote sensing images. Processing, storing and transmission via networks of a huge number of digital images requires considerable resources in the sense of memory, time, computational power, etc.
Makarichev, V.O. +4 more
openaire +1 more source
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
We propose a novel joint lossy image and residual compression framework for learning l ∞ -constrained near-lossless image compression. Specifically, we obtain a lossy reconstruction of the raw image through lossy image compression and uniformly quantize the corresponding residual to satisfy a given tight l ∞ error bound.
Yuanchao Bai +4 more
openaire +1 more source
We propose a novel joint lossy image and residual compression framework for learning l ∞ -constrained near-lossless image compression. Specifically, we obtain a lossy reconstruction of the raw image through lossy image compression and uniformly quantize the corresponding residual to satisfy a given tight l ∞ error bound.
Yuanchao Bai +4 more
openaire +1 more source
Quality Assessment for Hyperspectral Imagery: Comparison Between Lossy and Near-Lossless Compression
2006 Fortieth Asilomar Conference on Signals, Systems and Computers, 2006In the field of remote sensing image compression it is often argued that traditional MSE-based fidelity metrics might not effectively describe the quality of remote sensing lossy or near-lossless compressed images. In this paper we introduce a performance evaluation framework based on both reconstruction fidelity and impact on image exploitation ...
PENNA, BARBARA +3 more
openaire +2 more sources
Integrated lossy, near-lossless, and lossless compression of medical volumetric data
SPIE Proceedings, 2005We propose an integrated, wavelet based, two-stage coding scheme for lossy, near-lossless and lossless compression of medical volumetric data. The method presented determines the bit-rate while encoding for the lossy layer and without any iteration. It is in the spirit of "lossy plus residual coding" and consists of a wavelet-based lossy layer followed
Sehoon Yea +2 more
openaire +1 more source
Signal, Image and Video Processing, 2010
We investigate the ability to derive meaningful information from decompressed imaging spectrometer data. Hyperspectral images are compressed with near-lossless and lossy coding methods. Linear prediction between the bands is used in both cases. Each band is predicted by a previously transmitted band. The residual is formed by subtracting the prediction
Agnieszka Miguel +3 more
openaire +1 more source
We investigate the ability to derive meaningful information from decompressed imaging spectrometer data. Hyperspectral images are compressed with near-lossless and lossy coding methods. Linear prediction between the bands is used in both cases. Each band is predicted by a previously transmitted band. The residual is formed by subtracting the prediction
Agnieszka Miguel +3 more
openaire +1 more source
Journal of Micro/Nanolithography, MEMS, and MOEMS, 2015
Lossy and near-lossless digital hologram compression methods are investigated to compress different complexities of wafer surface structures. In the lossy compression method, we apply row- and column-based uniform downsampling together with spline interpolation, whereas in the near-lossless compression method, we use wavelet local modulus maxima and ...
Hongbo Zhang +6 more
openaire +1 more source
Lossy and near-lossless digital hologram compression methods are investigated to compress different complexities of wafer surface structures. In the lossy compression method, we apply row- and column-based uniform downsampling together with spline interpolation, whereas in the near-lossless compression method, we use wavelet local modulus maxima and ...
Hongbo Zhang +6 more
openaire +1 more source