Search Results for author: Zhouhui Lian

Found 34 papers, 20 papers with code

HFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, Faster Speed, and Higher Resolution

1 code implementation9 Oct 2024 Hua Li, Zhouhui Lian

Using our method, for the first time, large-scale Chinese vector fonts of a quality comparable to those manually created by professional font designers can be automatically generated.

Super-Resolution

Neural-Polyptych: Content Controllable Painting Recreation for Diverse Genres

no code implementations29 Sep 2024 Yiming Zhao, Dewen Guo, Zhouhui Lian, Yue Gao, Jianhong Han, Jie Feng, Guoping Wang, Bingfeng Zhou, Sheng Li

To bridge the gap between artists and non-specialists, we present a unified framework, Neural-Polyptych, to facilitate the creation of expansive, high-resolution paintings by seamlessly incorporating interactive hand-drawn sketches with fragments from original paintings.

Pano2Room: Novel View Synthesis from a Single Indoor Panorama

1 code implementation21 Aug 2024 Guo Pu, Yiming Zhao, Zhouhui Lian

The key idea is to initially construct a preliminary mesh from the input panorama, and iteratively refine this mesh using a panoramic RGBD inpainter while collecting photo-realistic 3D-consistent pseudo novel views.

Novel View Synthesis

Dynamic Texture Transfer using PatchMatch and Transformers

no code implementations1 Feb 2024 Guo Pu, Shiyao Xu, Xixin Cao, Zhouhui Lian

How to automatically transfer the dynamic texture of a given video to the target still image is a challenging and ongoing problem.

3DToonify: Creating Your High-Fidelity 3D Stylized Avatar Easily from 2D Portrait Images

no code implementations CVPR 2024 Yifang Men, Hanxi Liu, Yuan YAO, Miaomiao Cui, Xuansong Xie, Zhouhui Lian

In this paper we make a connection between the two and tackle the challenging task of 3D portrait stylization - modeling high-fidelity 3D stylized avatars from captured 2D portrait images.

Style Transfer

TextNeRF: A Novel Scene-Text Image Synthesis Method based on Neural Radiance Fields

1 code implementation CVPR 2024 Jialei Cui, Jianwei Du, Wenzhuo LIU, Zhouhui Lian

Acquiring large-scale well-annotated datasets is essential for training robust scene text detectors yet the process is often resource-intensive and time-consuming.

Image Generation Text Detection

SinMPI: Novel View Synthesis from a Single Image with Expanded Multiplane Images

1 code implementation18 Dec 2023 Guo Pu, Peng-Shuai Wang, Zhouhui Lian

This paper proposes SinMPI, a novel method that uses an expanded multiplane image (MPI) as the 3D scene representation to significantly expand the perspective range of MPI and generate high-quality novel views from a large multiplane space.

Novel View Synthesis

UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models

1 code implementation8 Dec 2023 Yiming Zhao, Zhouhui Lian

Text-to-Image (T2I) generation methods based on diffusion model have garnered significant attention in the last few years.

Image Generation Scene Text Editing

DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality

1 code implementation CVPR 2023 Yuqing Wang, Yizhi Wang, Longhui Yu, Yuesheng Zhu, Zhouhui Lian

First, we adopt Transformers instead of RNNs to process sequential data and design a relaxation representation for vector outlines, markedly improving the model's capability and stability of synthesizing long and complex outlines.

Decoder Vector Graphics

FontTransformer: Few-shot High-resolution Chinese Glyph Image Synthesis via Stacked Transformers

no code implementations12 Oct 2022 Yitian Liu, Zhouhui Lian

Automatic generation of high-quality Chinese fonts from a few online training samples is a challenging task, especially when the amount of samples is very small.

Few-Shot Learning Font Generation +1

DifferSketching: How Differently Do People Sketch 3D Objects?

1 code implementation19 Sep 2022 Chufeng Xiao, Wanchao Su, Jing Liao, Zhouhui Lian, Yi-Zhe Song, Hongbo Fu

We invited 70 novice users and 38 expert users to sketch 136 3D objects, which were presented as 362 images rendered from multiple views.

3D Reconstruction

DCT-Net: Domain-Calibrated Translation for Portrait Stylization

3 code implementations6 Jul 2022 Yifang Men, Yuan YAO, Miaomiao Cui, Zhouhui Lian, Xuansong Xie

This paper introduces DCT-Net, a novel image translation architecture for few-shot portrait stylization.

Few-Shot Learning Style Transfer +1

Aesthetic Text Logo Synthesis via Content-aware Layout Inferring

1 code implementation CVPR 2022 Yizhi Wang, Guo Pu, Wenhan Luo, Yexin Wang, Pengfei Xiong, Hongwen Kang, Zhouhui Lian

To train and evaluate our approach, we construct a dataset named as TextLogo3K, consisting of about 3, 500 text logo images and their pixel-level annotations.

Layout Design

Unpaired Cartoon Image Synthesis via Gated Cycle Mapping

no code implementations CVPR 2022 Yifang Men, Yuan YAO, Miaomiao Cui, Zhouhui Lian, Xuansong Xie, Xian-Sheng Hua

Experimental results demonstrate the superiority of the proposed method over the state of the art and validate its effectiveness in the brand-new task of general cartoon image synthesis.

Image Generation Video Generation

DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning

2 code implementations13 Oct 2021 Yizhi Wang, Zhouhui Lian

Automatic font generation based on deep learning has aroused a lot of interest in the last decade.

Font Generation Image Generation +1

Bidirectional Regression for Arbitrary-Shaped Text Detection

no code implementations13 Jul 2021 Tao Sheng, Zhouhui Lian

Arbitrary-shaped text detection has recently attracted increasing interests and witnessed rapid development with the popularity of deep learning algorithms.

regression Text Detection

Write like you: Synthesizing your cursive online Chinese handwriting via metric-based meta learning

1 code implementation Computer Graphics Forum 2021 Shusen Tang, Zhouhui Lian

Then, our entire model is trained in an end-to-end manner and the decoder adaptively receives the style information from the style encoder and the content information from the content encoder to synthesize the target output.

Decoder Meta-Learning +1

High-Fidelity and Arbitrary Face Editing

no code implementations CVPR 2021 Yue Gao, Fangyun Wei, Jianmin Bao, Shuyang Gu, Dong Chen, Fang Wen, Zhouhui Lian

However, we observe that the generator tends to find a tricky way to hide information from the original image to satisfy the constraint of cycle consistency, making it impossible to maintain the rich details (e. g., wrinkles and moles) of non-editing areas.

Attribute Vocal Bursts Intensity Prediction

Attribute2Font: Creating Fonts You Want From Attributes

2 code implementations16 May 2020 Yizhi Wang, Yue Gao, Zhouhui Lian

To the best of our knowledge, our model is the first one in the literature which is capable of generating glyph images in new font styles, instead of retrieving existing fonts, according to given values of specified font attributes.

Attribute Font Style Transfer

Controllable Person Image Synthesis with Attribute-Decomposed GAN

2 code implementations CVPR 2020 Yifang Men, Yiming Mao, Yuning Jiang, Wei-Ying Ma, Zhouhui Lian

This paper introduces the Attribute-Decomposed GAN, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes (e. g., pose, head, upper clothes and pants) provided in various source inputs.

Attribute continuous-control +2

FontRNN: Generating Large-scale Chinese Fonts via Recurrent Neural Network

1 code implementation Computer Graphics Forum 2019 Shusen Tang, Zeqing Xia, Zhouhui Lian, Yingmin Tang, Jianguo Xiao

Despite the recent impressive development of deep neural networks, using deep learning based methods to generate large-scale Chinese fonts is still a rather challenging task due to the huge number of intricate Chinese glyphs, e. g., the official standard Chinese charset GB18030-2000 consists of 27, 533 Chinese characters.

Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning

3 code implementations11 Oct 2019 Yue Gao, Yuan Guo, Zhouhui Lian, Yingmin Tang, Jianguo Xiao

Extensive experiments on both English and Chinese artistic glyph image datasets demonstrate the superiority of our model in generating high-quality stylized glyph images against other state-of-the-art methods.

Few-Shot Learning Image Generation

Boosting Scene Character Recognition by Learning Canonical Forms of Glyphs

1 code implementation12 Jul 2019 Yizhi Wang, Zhouhui Lian, Yingmin Tang, Jianguo Xiao

In this paper, we propose a novel methodology for boosting scene character recognition by learning canonical forms of glyphs, based on the fact that characters appearing in scene images are all derived from their corresponding canonical forms.

A Common Framework for Interactive Texture Transfer

no code implementations CVPR 2018 Yifang Men, Zhouhui Lian, Yingmin Tang, Jianguo Xiao

In this paper, we present a general-purpose solution to interactive texture transfer problems that better preserves both local structure and visual richness.

Diversity

Incremental Kernel Null Space Discriminant Analysis for Novelty Detection

no code implementations CVPR 2017 Juncheng Liu, Zhouhui Lian, Yi Wang, Jianguo Xiao

This validates the superiority of our IKNDA against the state of the art in novelty detection for large-scale data.

Novelty Detection

Awesome Typography: Statistics-Based Text Effects Transfer

1 code implementation CVPR 2017 Shuai Yang, Jiaying Liu, Zhouhui Lian, Zongming Guo

It allows our algorithm to produce artistic typography that fits for both local texture patterns and the global spatial distribution in the example.

Style Transfer Text Effects Transfer +1

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