Search Results for author: Li-Wen Wang

Found 14 papers, 10 papers with code

Multiple-level Green Noise Mask Design for Practical Fourier Phase Retrieval

no code implementations28 Mar 2023 Qiuliang Ye, Bingo Wing-Kuen Ling, Li-Wen Wang, Daniel Pak-Kong Lun

This paper proposes a two-stage optimization algorithm to generate multi-level random masks named $\textit{OptMask}$ that can also significantly reduce high-frequency components in the measurements but achieve higher accuracy than the binary masking scheme.


Towards Practical Single-shot Phase Retrieval with Physics-Driven Deep Neural Network

no code implementations18 Aug 2022 Qiuliang Ye, Li-Wen Wang, Daniel Pak-Kong Lun

The results demonstrate the superiority and practicality of the proposed PPRNet over the traditional learning-based PR methods.

Quantization Retrieval

SiSPRNet: End-to-End Learning for Single-Shot Phase Retrieval

1 code implementation23 May 2022 Qiuliang Ye, Li-Wen Wang, Daniel P. K. Lun

With the success of deep learning methods in many image processing tasks, deep learning approaches have also been introduced to the phase retrieval problem recently.

Image Reconstruction Retrieval

Name Your Style: An Arbitrary Artist-aware Image Style Transfer

1 code implementation28 Feb 2022 Zhi-Song Liu, Li-Wen Wang, Wan-Chi Siu, Vicky Kalogeiton

Moreover, it can mimic the styles of one or many artists to achieve attractive results, thus highlighting a promising direction in image style transfer.

Style Transfer

Variational AutoEncoder for Reference based Image Super-Resolution

1 code implementation8 Jun 2021 Zhi-Song Liu, Wan-Chi Siu, Li-Wen Wang

In this paper, we propose a novel reference based image super-resolution approach via Variational AutoEncoder (RefVAE).

Image Super-Resolution SSIM

Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise

no code implementations8 Oct 2020 Zixun Huang, Li-Wen Wang, Frank H. F. Leung, Sunetra Banerjee, De Yang, Timothy Lee, Juan Lyu, Sai Ho Ling, Yong-Ping Zheng

In this paper, we propose a robust bone feature segmentation method based on the U-net structure for ultrasound spine Volume Projection Imaging (VPI) images.


Deep Relighting Networks for Image Light Source Manipulation

1 code implementation19 Aug 2020 Li-Wen Wang, Wan-Chi Siu, Zhi-Song Liu, Chu-Tak Li, Daniel P. K. Lun

Manipulating the light source of given images is an interesting task and useful in various applications, including photography and cinematography.

Image Relighting

DeepGIN: Deep Generative Inpainting Network for Extreme Image Inpainting

1 code implementation17 Aug 2020 Chu-Tak Li, Wan-Chi Siu, Zhi-Song Liu, Li-Wen Wang, Daniel Pak-Kong Lun

Existing image inpainting approaches usually encounter difficulties in completing the missing parts in the wild with pleasing visual and contextual results as they are trained for either dealing with one specific type of missing patterns (mask) or unilaterally assuming the shapes and/or sizes of the masked areas.

Image Inpainting

Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder

1 code implementation27 Apr 2020 Zhi-Song Liu, Wan-Chi Siu, Li-Wen Wang, Chu-Tak Li, Marie-Paule Cani, Yui-Lam Chan

Depending upon whether using a discriminator or not, a deep convolutional neural network can provide an image with high fidelity or better perceptual quality.

Decoder Image Denoising +1

Hierarchical Back Projection Network for Image Super-Resolution

1 code implementation17 Jun 2019 Zhi-Song Liu, Li-Wen Wang, Chu-Tak Li, Wan-Chi Siu

We propose a Hierarchical Back Projection Network (HBPN), that cascades multiple HourGlass (HG) modules to bottom-up and top-down process features across all scales to capture various spatial correlations and then consolidates the best representation for reconstruction.

Image Super-Resolution

Cannot find the paper you are looking for? You can Submit a new open access paper.