中文
相关论文

相关论文: CF-Font: Content Fusion for Few-shot Font Generati…

200 篇论文

Training a generative model with limited number of samples is a challenging task. Current methods primarily rely on few-shot model adaption to train the network. However, in scenarios where data is extremely limited (less than 10), the…

计算机视觉与模式识别 · 计算机科学 2023-09-08 Teng Hu , Jiangning Zhang , Liang Liu , Ran Yi , Siqi Kou , Haokun Zhu , Xu Chen , Yabiao Wang , Chengjie Wang , Lizhuang Ma

Chinese character synthesis involves two related aspects, i.e., style maintenance and content consistency. Although some methods have achieved remarkable success in synthesizing a character with specified style from standard font, how to…

计算机视觉与模式识别 · 计算机科学 2019-10-29 Xiyan Liu , Gaofeng Meng , Shiming Xiang , Chunhong Pan

Few-shot font generation aims to create new fonts with a limited number of glyph references. It can be used to significantly reduce the labor cost of manual font design. However, due to the variety and complexity of font styles, the results…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Weiran Chen , Guiqian Zhu , Ying Li , Yi Ji , Chunping Liu

Due to the absence of fine structure and texture information, existing fusion-based few-shot image generation methods suffer from unsatisfactory generation quality and diversity. To address this problem, we propose a novel feature…

计算机视觉与模式识别 · 计算机科学 2023-07-28 Yingbo Zhou , Zhihao Yue , Yutong Ye , Pengyu Zhang , Xian Wei , Mingsong Chen

Automatic font generation remains a challenging research issue due to the large amounts of characters with complicated structures. Typically, only a few samples can serve as the style/content reference (termed few-shot learning), which…

计算机视觉与模式识别 · 计算机科学 2022-05-10 Yuxin Kong , Canjie Luo , Weihong Ma , Qiyuan Zhu , Shenggao Zhu , Nicholas Yuan , Lianwen Jin

Generating a new font library is a very labor-intensive and time-consuming job for glyph-rich scripts. Despite the remarkable success of existing font generation methods, they have significant drawbacks; they require a large number of…

计算机视觉与模式识别 · 计算机科学 2020-07-17 Junbum Cha , Sanghyuk Chun , Gayoung Lee , Bado Lee , Seonghyeon Kim , Hwalsuk Lee

Few-shot image generation seeks to generate more data of a given domain, with only few available training examples. As it is unreasonable to expect to fully infer the distribution from just a few observations (e.g., emojis), we seek to…

计算机视觉与模式识别 · 计算机科学 2020-12-07 Yijun Li , Richard Zhang , Jingwan Lu , Eli Shechtman

In this paper, we demonstrate a total disentanglement of font images. Total disentanglement is a neural network-based method for decomposing each font image nonlinearly and completely into its style and content (i.e., character class)…

计算机视觉与模式识别 · 计算机科学 2025-09-12 Daichi Haraguchi , Wataru Shimoda , Kota Yamaguchi , Seiichi Uchida

Few-shot image generation, which aims to produce plausible and diverse images for one category given a few images from this category, has drawn extensive attention. Existing approaches either globally interpolate different images or fuse…

计算机视觉与模式识别 · 计算机科学 2023-08-31 Mengping Yang , Zhe Wang , Wenyi Feng , Qian Zhang , Ting Xiao

Lifelong few-shot customization for text-to-image diffusion aims to continually generalize existing models for new tasks with minimal data while preserving old knowledge. Current customization diffusion models excel in few-shot tasks but…

计算机视觉与模式识别 · 计算机科学 2024-11-11 Nan Song , Xiaofeng Yang , Ze Yang , Guosheng Lin

Font synthesis has been a very active topic in recent years because manual font design requires domain expertise and is a labor-intensive and time-consuming job. While remarkably successful, existing methods for font synthesis have major…

计算机视觉与模式识别 · 计算机科学 2022-05-16 Ammar Ul Hassan Muhammad , Jaeyoung Choi

For better explore the relations of inter-modal and inner-modal, even in deep learning fusion framework, the concept of decomposition plays a crucial role. However, the previous decomposition strategies (base \& detail or low-frequency \&…

计算机视觉与模式识别 · 计算机科学 2024-12-04 Hui Li , Haolong Ma , Chunyang Cheng , Zhongwei Shen , Xiaoning Song , Xiao-Jun Wu

The challenge of automatically synthesizing high-quality vector fonts, particularly for writing systems (e.g., Chinese) consisting of huge amounts of complex glyphs, remains unsolved. Existing font synthesis techniques fall into two…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Hua Li , Zhouhui Lian

Textual image generation spans diverse fields like advertising, education, product packaging, social media, information visualization, and branding. Despite recent strides in language-guided image synthesis using diffusion models, current…

计算机视觉与模式识别 · 计算机科学 2024-05-22 Shubham Paliwal , Arushi Jain , Monika Sharma , Vikram Jamwal , Lovekesh Vig

Multi-modality image fusion aims to combine different modalities to produce fused images that retain the complementary features of each modality, such as functional highlights and texture details. To leverage strong generative priors and…

计算机视觉与模式识别 · 计算机科学 2023-08-24 Zixiang Zhao , Haowen Bai , Yuanzhi Zhu , Jiangshe Zhang , Shuang Xu , Yulun Zhang , Kai Zhang , Deyu Meng , Radu Timofte , Luc Van Gool

Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Huayi Zhu , Xiu Shu , Youqiang Xiong , Qiao Liu , Rui Chen , Di Yuan , Xiaojun Chang , Zhenyu He

Fashion content generation is an emerging area at the intersection of artificial intelligence and creative design, with applications ranging from virtual try-on to culturally diverse design prototyping. Existing methods often struggle with…

计算与语言 · 计算机科学 2025-01-28 Spencer Ramsey , Amina Grant , Jeffrey Lee

Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud…

计算机视觉与模式识别 · 计算机科学 2025-02-27 Zhaochong An , Guolei Sun , Yun Liu , Runjia Li , Min Wu , Ming-Ming Cheng , Ender Konukoglu , Serge Belongie

Image Generation models are a trending topic nowadays, with many people utilizing Artificial Intelligence models in order to generate images. There are many such models which, given a prompt of a text, will generate an image which depicts…

机器学习 · 计算机科学 2025-05-20 Udaya Shreyas , L. N. Aadarsh

Existing multi-modal image fusion methods fail to address the compound degradations presented in source images, resulting in fusion images plagued by noise, color bias, improper exposure, \textit{etc}. Additionally, these methods often…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Hao Zhang , Lei Cao , Jiayi Ma