Search Results for author: Dongming Lu

Found 15 papers, 7 papers with code

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

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.

Style Transfer

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

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.

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

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

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