Search Results for author: Zhi-Song Liu

Found 19 papers, 12 papers with code

Bridging Text and Image for Artist Style Transfer via Contrastive Learning

no code implementations12 Oct 2024 Zhi-Song Liu, Li-Wen Wang, Jun Xiao, Vicky Kalogeiton

In this paper, we propose a Contrastive Learning for Artistic Style Transfer (CLAST) that leverages advanced image-text encoders to control arbitrary style transfer.

Contrastive Learning State Space Models +1

Super-Resolution works for coastal simulations

no code implementations29 Aug 2024 Zhi-Song Liu, Markus Buttner, Vadym Aizinger, Andreas Rupp

To efficiently model the dynamic changes over time and space, we propose grid-aware spatiotemporal attention to project the temporal features to the spatial domain for non-local feature matching.

Model Optimization Super-Resolution

Neural Network Emulator for Atmospheric Chemical ODE

no code implementations3 Aug 2024 Zhi-Song Liu, Petri Clusius, Michael Boy

To extract the hidden correlations between initial states and future time evolution, we propose ChemNNE, an Attention based Neural Network Emulator (NNE) that can model the atmospheric chemistry as a neural ODE process.

StyleMamba : State Space Model for Efficient Text-driven Image Style Transfer

no code implementations8 May 2024 Zijia Wang, Zhi-Song Liu

We present StyleMamba, an efficient image style transfer framework that translates text prompts into corresponding visual styles while preserving the content integrity of the original images.

Style Transfer

FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild

1 code implementation8 Jan 2024 Zhi-Song Liu, Robin Courant, Vicky Kalogeiton

In this paper, we propose FunnyNet-W, a model that relies on cross- and self-attention for visual, audio and text data to predict funny moments in videos.

Language Modelling Large Language Model +1

See360: Novel Panoramic View Interpolation

1 code implementation7 Jan 2024 Zhi-Song Liu, Marie-Paule Cani, Wan-Chi Siu

We present See360, which is a versatile and efficient framework for 360 panoramic view interpolation using latent space viewpoint estimation.

Viewpoint Estimation

Soft-IntroVAE for Continuous Latent space Image Super-Resolution

no code implementations18 Jul 2023 Zhi-Song Liu, Zijia Wang, Zhen Jia

Continuous image super-resolution (SR) recently receives a lot of attention from researchers, for its practical and flexible image scaling for various displays.

Denoising Image Restoration +1

Arbitrary point cloud upsampling via Dual Back-Projection Network

no code implementations18 Jul 2023 Zhi-Song Liu, Zijia Wang, Zhen Jia

Point cloud upsampling is an approach to increase the density of the point cloud so that detailed geometric information can be restored.

point cloud upsampling set matching

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

Multiple Style Transfer via Variational AutoEncoder

1 code implementation13 Oct 2021 Zhi-Song Liu, Vicky Kalogeiton, Marie-Paule Cani

Modern works on style transfer focus on transferring style from a single image.

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

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.