5 papers
Removing Motion Artifact in MRI by Using a Perceptual Loss Driven Deep Learning Framework
Ziheng Guo, Danqun Zheng, Shuai Li +8
Purpose: Deep learning-based MRI artifact correction methods often demonstrate poor generalization to clinical data. This limitation largely stems from the inability of deep learni…
Monocular Depth Estimation From the Perspective of Feature Restoration: A Diffusion Enhanced Depth Restoration Approach
Huibin Bai, Shuai Li, Hanxiao Zhai +6
Monocular Depth Estimation (MDE) is a fundamental computer vision task with important applications in 3D vision. The current mainstream MDE methods employ an encoder-decoder archit…
A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression
Zhenyu Du, Yanbo Gao, Shuai Li +3
With the great success of diffusion models in image generation, diffusion-based image compression is attracting increasing interests. However, due to the random noise introduced in…
Interleaved Block-based Learned Image Compression with Feature Enhancement and Quantization Error Compensation
Shiqi Jiang, Hui Yuan, Shuai Li +3
In recent years, learned image compression (LIC) methods have achieved significant performance improvements. However, obtaining a more compact latent representation and reducing th…
FD-LSCIC: Frequency Decomposition-based Learned Screen Content Image Compression
Shiqi Jiang, Hui Yuan, Shuai Li +2
The learned image compression (LIC) methods have already surpassed traditional techniques in compressing natural scene (NS) images. However, directly applying these methods to scre…