paper-with-me

Papers

Text2Poster: Laying out Stylized Texts on Retrieved Images

2023-01-06 · Chuhao Jin, Hongteng Xu, Ruihua Song, Zhiwu Lu

Poster generation is a significant task for a wide range of applications, which is often time-consuming and requires lots of manual editing and artistic experience. In this paper, we propose a novel data-driven framework, called \textit{Text2Poster}, to automatically generate visually-effective posters from textual information. Imitating the process of manual poster editing, our framework leverages a large-scale pretrained visual-textual model to retrieve background images from given texts, lays out the texts on the images iteratively by cascaded auto-encoders, and finally, stylizes the texts by a matching-based method. We learn the modules of the framework by weakly- and self-supervised learning strategies, mitigating the demand for labeled data. Both objective and subjective experiments demonstrate that our Text2Poster outperforms state-of-the-art methods, including academic research and commercial software, on the quality of generated posters.

📄 PDF Abstract BibTeX arXiv:2301.02363

Code (1)

chuhaojin/text2poster-icassp-22 공식 구현 pytorch

Tasks

Image RetrievalLayout Designmultimodal generation

Similar Papers 제목 키워드 기반

Stylized Dialogue Response Generation Using Stylized Unpaired Texts

2020-09-27 · Yinhe Zheng, Zikai Chen, Rongsheng Zhang, Shilei Huang 외

Generating stylized responses is essential to build intelligent and engaging dialogue systems. However, this task is far from well-explored due to the difficulties of rendering a particular style in coherent responses, e…

DecoderDialogue GenerationResponse Generation

De-rendering Stylized Texts

2021-10-05 · ICCV 2021 10 · Wataru Shimoda, Daichi Haraguchi, Seiichi Uchida, Kota Yamaguchi

Editing raster text is a promising but challenging task. We propose to apply text vectorization for the task of raster text editing in display media, such as posters, web pages, or advertisements. In our approach, instea…

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?

2024-01-22 · Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang 외

While auxiliary information has become a key to enhancing Large Language Models (LLMs), relatively little is known about how LLMs merge these contexts, specifically contexts generated by LLMs and those retrieved from ext…

Misinformation

Stylized Dialogue Generation with Multi-Pass Dual Learning

2021-12-01 · NeurIPS 2021 12 · Jinpeng Li, Yingce Xia, Rui Yan, Hongda Sun 외

Stylized dialogue generation, which aims to generate a given-style response for an input context, plays a vital role in intelligent dialogue systems. Considering there is no parallel data between the contexts and the res…

Dialogue Generation

SMooDi: Stylized Motion Diffusion Model

2024-07-17 · Lei Zhong, Yiming Xie, Varun Jampani, Deqing Sun 외

We introduce a novel Stylized Motion Diffusion model, dubbed SMooDi, to generate stylized motion driven by content texts and style motion sequences. Unlike existing methods that either generate motion of various content …

modelMotion Generation