Search Results for author: Wei Xing

Found 32 papers, 16 papers with code

Towards Highly Realistic Artistic Style Transfer via Stable Diffusion with Step-aware and Layer-aware Prompt

1 code implementation17 Apr 2024 Zhanjie Zhang, Quanwei Zhang, Huaizhong Lin, Wei Xing, Juncheng Mo, Shuaicheng Huang, Jinheng Xie, Guangyuan Li, Junsheng Luan, Lei Zhao, Dalong Zhang, Lixia Chen

To address the above problems, we propose a novel pre-trained diffusion-based artistic style transfer method, called LSAST, which can generate highly realistic artistic stylized images while preserving the content structure of input content images well, without bringing obvious artifacts and disharmonious style patterns.

Generative Adversarial Network Style Transfer

Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution

1 code implementation7 Apr 2024 Guangyuan Li, Chen Rao, Juncheng Mo, Zhanjie Zhang, Wei Xing, Lei Zhao

Recently, diffusion models (DM) have been applied in magnetic resonance imaging (MRI) super-resolution (SR) reconstruction, exhibiting impressive performance, especially with regard to detailed reconstruction.

Decoder Super-Resolution

PNeSM: Arbitrary 3D Scene Stylization via Prompt-Based Neural Style Mapping

no code implementations13 Mar 2024 Jiafu Chen, Wei Xing, Jiakai Sun, Tianyi Chu, Yiling Huang, Boyan Ji, Lei Zhao, Huaizhong Lin, Haibo Chen, Zhizhong Wang

3D scene stylization refers to transform the appearance of a 3D scene to match a given style image, ensuring that images rendered from different viewpoints exhibit the same style as the given style image, while maintaining the 3D consistency of the stylized scene.


Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation

no code implementations13 Mar 2024 Tianyi Chu, Wei Xing, Jiafu Chen, Zhizhong Wang, Jiakai Sun, Lei Zhao, Haibo Chen, Huaizhong Lin

Given that many deterministic conditional image generative models have been able to produce high-quality yet fixed results, we raise an intriguing question: is it possible for pre-trained deterministic conditional image generative models to generate diverse results without changing network structures or parameters?

Adversarial Attack Conditional Image Generation +3

3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos

1 code implementation3 Mar 2024 Jiakai Sun, Han Jiao, Guangyuan Li, Zhanjie Zhang, Lei Zhao, Wei Xing

Constructing photo-realistic Free-Viewpoint Videos (FVVs) of dynamic scenes from multi-view videos remains a challenging endeavor.

Neural Rendering

ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank

1 code implementation11 Dec 2023 Zhanjie Zhang, Quanwei Zhang, Guangyuan Li, Wei Xing, Lei Zhao, Jiakai Sun, Zehua Lan, Junsheng Luan, Yiling Huang, Huaizhong Lin

To address the above issues, we propose ArtBank, a novel artistic style transfer framework, to generate highly realistic stylized images while preserving the content structure of the content images.

Style Transfer

Multi-Resolution Active Learning of Fourier Neural Operators

1 code implementation29 Sep 2023 Shibo Li, Xin Yu, Wei Xing, Mike Kirby, Akil Narayan, Shandian Zhe

To overcome this problem, we propose Multi-Resolution Active learning of FNO (MRA-FNO), which can dynamically select the input functions and resolutions to lower the data cost as much as possible while optimizing the learning efficiency.

Active Learning LEMMA +2

StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models

no code implementations ICCV 2023 Zhizhong Wang, Lei Zhao, Wei Xing

Our work provides new insights into the C-S disentanglement in style transfer and demonstrates the potential of diffusion models for learning well-disentangled C-S characteristics.

Disentanglement Style Transfer

VGOS: Voxel Grid Optimization for View Synthesis from Sparse Inputs

1 code implementation26 Apr 2023 Jiakai Sun, Zhanjie Zhang, Jiafu Chen, Guangyuan Li, Boyan Ji, Lei Zhao, Wei Xing, Huaizhong Lin

In this paper, we propose VGOS, an approach for fast (3-5 minutes) radiance field reconstruction from sparse inputs (3-10 views) to address these issues.

Novel View Synthesis

Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning

1 code implementation23 Mar 2023 Zhiwen Zuo, Lei Zhao, Ailin Li, Zhizhong Wang, Zhanjie Zhang, Jiafu Chen, Wei Xing, Dongming Lu

By combining SCAT with standard global adversarial training, the new adversarial training framework exhibits the following three advantages simultaneously: (1) the global consistency of the repaired image, (2) the local fine texture details of the repaired image, and (3) the flexibility of handling images with free-form holes.

Contrastive Learning Image Inpainting

Rethinking Fast Fourier Convolution in Image Inpainting

no code implementations ICCV 2023 Tianyi Chu, Jiafu Chen, Jiakai Sun, Shuobin Lian, Zhizhong Wang, Zhiwen Zuo, Lei Zhao, Wei Xing, Dongming Lu

Recently proposed image inpainting method LaMa builds its network upon Fast Fourier Convolution (FFC), which was originally proposed for high-level vision tasks like image classification.

Image Classification Image Inpainting

Rethinking Multi-Contrast MRI Super-Resolution: Rectangle-Window Cross-Attention Transformer and Arbitrary-Scale Upsampling

no code implementations ICCV 2023 Guangyuan Li, Lei Zhao, Jiakai Sun, Zehua Lan, Zhanjie Zhang, Jiafu Chen, Zhijie Lin, Huaizhong Lin, Wei Xing

Recently, several methods have explored the potential of multi-contrast magnetic resonance imaging (MRI) super-resolution (SR) and obtain results superior to single-contrast SR methods.


MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfer

1 code implementation28 Nov 2022 Zhizhong Wang, Lei Zhao, Zhiwen Zuo, Ailin Li, Haibo Chen, Wei Xing, Dongming Lu

The style encoder, coupled with a modulator, encodes the style image into learnable dual-modulation signals that modulate both intermediate features and convolutional filters of the decoder, thus injecting more sophisticated and flexible style signals to guide the stylizations.

4k Decoder +1

AesUST: Towards Aesthetic-Enhanced Universal Style Transfer

1 code implementation27 Aug 2022 Zhizhong Wang, Zhanjie Zhang, Lei Zhao, Zhiwen Zuo, Ailin Li, Wei Xing, Dongming Lu

Specifically, our approach introduces an aesthetic discriminator to learn the universal human-delightful aesthetic features from a large corpus of artist-created paintings.

Style Transfer

Texture Reformer: Towards Fast and Universal Interactive Texture Transfer

1 code implementation6 Dec 2021 Zhizhong Wang, Lei Zhao, Haibo Chen, Ailin Li, Zhiwen Zuo, Wei Xing, Dongming Lu

In addition, we also introduce a novel learning-free view-specific texture reformation (VSTR) operation with a new semantic map guidance strategy to achieve more accurate semantic-guided and structure-preserved texture transfer.

Artistic Style Transfer with Internal-external Learning and Contrastive Learning

1 code implementation NeurIPS 2021 Haibo Chen, Lei Zhao, Zhizhong Wang, Huiming Zhang, Zhiwen Zuo, Ailin Li, Wei Xing, Dongming Lu

Although existing artistic style transfer methods have achieved significant improvement with deep neural networks, they still suffer from artifacts such as disharmonious colors and repetitive patterns.

Contrastive Learning Style Transfer

DualAST: Dual Style-Learning Networks for Artistic Style Transfer

no code implementations CVPR 2021 Haibo Chen, Lei Zhao, Zhizhong Wang, Huiming Zhang, Zhiwen Zuo, Ailin Li, Wei Xing, Dongming Lu

Artistic style transfer is an image editing task that aims at repainting everyday photographs with learned artistic styles.

Style Transfer

Multimodal Image-to-Image Translation via Mutual Information Estimation and Maximization

no code implementations8 Aug 2020 Zhiwen Zuo, Lei Zhao, Zhizhong Wang, Haibo Chen, Ailin Li, Qijiang Xu, Wei Xing, Dongming Lu

Multimodal image-to-image translation (I2IT) aims to learn a conditional distribution that explores multiple possible images in the target domain given an input image in the source domain.

Disentanglement Image-to-Image Translation +2

Multi-Fidelity Bayesian Optimization via Deep Neural Networks

no code implementations NeurIPS 2020 Shibo Li, Wei Xing, Mike Kirby, Shandian Zhe

In many applications, the objective function can be evaluated at multiple fidelities to enable a trade-off between the cost and accuracy.

Bayesian Optimization

Multi-Fidelity High-Order Gaussian Processes for Physical Simulation

1 code implementation8 Jun 2020 Zheng Wang, Wei Xing, Robert Kirby, Shandian Zhe

To address these issues, we propose Multi-Fidelity High-Order Gaussian Process (MFHoGP) that can capture complex correlations both between the outputs and between the fidelities to enhance solution estimation, and scale to large numbers of outputs.

Gaussian Processes Vocal Bursts Intensity Prediction

Physics Informed Deep Kernel Learning

no code implementations8 Jun 2020 Zheng Wang, Wei Xing, Robert Kirby, Shandian Zhe

Deep kernel learning is a promising combination of deep neural networks and nonparametric function learning.

Gaussian Processes Uncertainty Quantification

Scalable Variational Gaussian Process Regression Networks

2 code implementations25 Mar 2020 Shibo Li, Wei Xing, Mike Kirby, Shandian Zhe

Gaussian process regression networks (GPRN) are powerful Bayesian models for multi-output regression, but their inference is intractable.

regression Variational Inference

Cascade Style Transfer

no code implementations ICLR 2020 Zhizhong Wang, Lei Zhao, Qihang Mo, Sihuan Lin, Zhiwen Zuo, Wei Xing, Dongming Lu

This could help improve the quality and flexibility, and guide us to find domain-independent approaches.

Serial Style Transfer

LDMGAN: Reducing Mode Collapse in GANs with Latent Distribution Matching

no code implementations ICLR 2020 Zhiwen Zuo, Lei Zhao, Huiming Zhang, Qihang Mo, Haibo Chen, Zhizhong Wang, Ailin Li, Lihong Qiu, Wei Xing, Dongming Lu

Generative Adversarial Networks (GANs) have shown impressive results in modeling distributions over complicated manifolds such as those of natural images.

Diversified Arbitrary Style Transfer via Deep Feature Perturbation

2 code implementations CVPR 2020 Zhizhong Wang, Lei Zhao, Haibo Chen, Lihong Qiu, Qihang Mo, Sihuan Lin, Wei Xing, Dongming Lu

Image style transfer is an underdetermined problem, where a large number of solutions can satisfy the same constraint (the content and style).

Style Transfer

On Compression of Unsupervised Neural Nets by Pruning Weak Connections

no code implementations21 Jan 2019 Zhiwen Zuo, Lei Zhao, Liwen Zuo, Feng Jiang, Wei Xing, Dongming Lu

Unsupervised neural nets such as Restricted Boltzmann Machines(RBMs) and Deep Belif Networks(DBNs), are powerful in automatic feature extraction, unsupervised weight initialization and density estimation.

Density Estimation

GLStyleNet: Higher Quality Style Transfer Combining Global and Local Pyramid Features

1 code implementation18 Nov 2018 Zhizhong Wang, Lei Zhao, Wei Xing, Dongming Lu

Our approach is not only flexible to adjust the trade-off between content and style, but also controllable between global and local.

Style Transfer

Adversarial Prediction Games for Multivariate Losses

no code implementations NeurIPS 2015 Hong Wang, Wei Xing, Kaiser Asif, Brian Ziebart

Multivariate loss functions are used to assess performance in many modern prediction tasks, including information retrieval and ranking applications.

Information Retrieval Retrieval

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