Learned image compression with mixed transformer-cnn architectures
Learned image compression (LIC) methods have exhibited promising progress and superior
rate-distortion performance compared with classical image compression standards. Most …
rate-distortion performance compared with classical image compression standards. Most …
Elic: Efficient learned image compression with unevenly grouped space-channel contextual adaptive coding
Recently, learned image compression techniques have achieved remarkable performance,
even surpassing the best manually designed lossy image coders. They are promising to be …
even surpassing the best manually designed lossy image coders. They are promising to be …
Asymmetric learned image compression with multi-scale residual block, importance scaling, and post-quantization filtering
Recently, deep learning-based image compression has made significant progresses, and
has achieved better rate-distortion (RD) performance than the latest traditional method, H …
has achieved better rate-distortion (RD) performance than the latest traditional method, H …
End-to-end learning-based image compression with a decoupled framework
The autoregressive model has been widely used in learning-based image compression due
to its superior context modeling capability. However, its sequential processing nature also …
to its superior context modeling capability. However, its sequential processing nature also …
Learned image compression with generalized octave convolution and cross-resolution parameter estimation
Recently, image compression approaches based on deep learning have gradually
outperformed existing image compression standards including BPG and VVC intra coding …
outperformed existing image compression standards including BPG and VVC intra coding …
Nonlinear transforms in learned image compression from a communication perspective
Recently, remarkable progress has been made in learned image compression (LIC), in
which nonlinear transforms (NTs) play a crucial role. Although there are many NT methods …
which nonlinear transforms (NTs) play a crucial role. Although there are many NT methods …
Hyperspectral image compression via cross-channel contrastive learning
Y Guo, Y Chong, S Pan - IEEE Transactions on Geoscience …, 2023 - ieeexplore.ieee.org
In recent years, advances in deep learning have greatly promoted the development of
hyperspectral image (HSI) compression algorithms. However, most existing compression …
hyperspectral image (HSI) compression algorithms. However, most existing compression …
Multi-context dual hyper-prior neural image compression
Transform and entropy models are the two core components in deep image compression
neural networks. Most existing learning-based image compression methods utilize …
neural networks. Most existing learning-based image compression methods utilize …
Super-High-Fidelity Image Compression via Hierarchical-ROI and Adaptive Quantization
Learned Image Compression (LIC) has achieved dramatic progress regarding objective and
subjective metrics. MSE-based models aim to improve objective metrics while generative …
subjective metrics. MSE-based models aim to improve objective metrics while generative …
Fourier Series and Laplacian Noise-Based Quantization Error Compensation for End-to-End Learning-Based Image Compression
Quantization is a core operation in lossy image compression. In the end-to-end learning-
based image compression framework, quantization is conducted by a rounding operation …
based image compression framework, quantization is conducted by a rounding operation …