Recently, multi-reference entropy model has been proposed, which captures
channel-wise, local spatial, and global spatial correlations. Previous works
adopt attention for global correlation capturing, however, the quadratic
cpmplexity limits the potential of high-resolution image coding. In this paper,
we propose the linear complexity global correlations capturing, via the
decomposition of softmax operation. Based on it, we propose the MLIC$^{++}$, a
learned image compression with linear complexity for multi-reference entropy
modeling. Our MLIC$^{++}$ is more efficient and it reduces BD-rate by 12.44% on
the Kodak dataset compared to VTM-17.0 when measured in PSNR. Code will be
available at this https URL

通过对 softmax 运算的分解，本文提出了线性复杂度的全局相关性捕获方法，从而提出了 MLIC$^{++}$，一种具有线性复杂度的用于多参考熵建模的学习图像压缩方法。与 VTM-17.0 相比，我们的 MLIC$^{++}$ 在 PSNR 上在 Kodak 数据集上将 BD 率降低了 12.44%。

MLIC++：线性复杂度多参考熵建模的学习图像压缩

MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned  Image Compression

Global correlations are widely seen in human anatomical structures due to
similarity across tissues and bones. These correlations are reflected in
magnetic resonance imaging (MRI) scans as a result of close-range proton
density and T1/T2 parameters. Furthermore, to achieve accelerated MRI, k-space
data are undersampled which causes global aliasing artifacts. Convolutional
neural network (CNN) models are widely utilized for accelerated MRI
reconstruction, but those models are limited in capturing global correlations
due to the intrinsic locality of the convolution operation. The
self-attention-based transformer models are capable of capturing global
correlations among image features, however, the current contributions of
transformer models for MRI reconstruction are minute. The existing
contributions mostly provide CNN-transformer hybrid solutions and rarely
leverage the physics of MRI. In this paper, we propose a physics-based
stand-alone (convolution free) transformer model titled, the Multi-head
Cascaded Swin Transformers (McSTRA) for accelerated MRI reconstruction. McSTRA
combines several interconnected MRI physics-related concepts with the
transformer networks: it exploits global MR features via the shifted window
self-attention mechanism; it extracts MR features belonging to different
spectral components separately using a multi-head setup; it iterates between
intermediate de-aliasing and k-space correction via a cascaded network with
data consistency in k-space and intermediate loss computations; furthermore, we
propose a novel positional embedding generation mechanism to guide
self-attention utilizing the point spread function corresponding to the
undersampling mask. Our model significantly outperforms state-of-the-art MRI
reconstruction methods both visually and quantitatively while depicting
improved resolution and removal of aliasing artifacts.

本文提出了一种基于物理学的独立变压器模型（Multi-head Cascaded Swin Transformers，McSTRA），用于快速磁共振成像重建，该模型结合了多个相互连接的磁共振物理相关的概念与变压器网络，具有窗口自注意机制、多头设置、级联网络等特点，并采用一种新颖的位置嵌入机制，显著优于现有 MRI 重建方法，提高了图像的分辨率和去除了混淆伪影。