中文
相关论文

相关论文: All Seeds Are Not Equal: Enhancing Compositional T…

200 篇论文

Diffusion methods have been proven to be very effective to generate images while conditioning on a text prompt. However, and although the quality of the generated images is unprecedented, these methods seem to struggle when trying to…

计算机视觉与模式识别 · 计算机科学 2023-02-07 Álvaro Barbero Jiménez

Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts, but they pose safety concerns because they can generate offensive or disturbing imagery when provided with harmful inputs. Existing…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Chi Zhang , Changjia Zhu , Xiaowen Li , Yao Liu , Zhuo Lu

Text-to-image (T2I) generation has seen significant progress with diffusion models, enabling generation of photo-realistic images from text prompts. Despite this progress, existing methods still face challenges in following complex text…

计算机视觉与模式识别 · 计算机科学 2025-03-12 Ashish Goswami , Satyam Kumar Modi , Santhosh Rishi Deshineni , Harman Singh , Prathosh A. P , Parag Singla

Text-to-image generative models have recently garnered significant attention due to their ability to generate images based on prompt descriptions. While these models have shown promising performance, concerns have been raised regarding the…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Meiling Li , Zhenxing Qian , Xinpeng Zhang

We introduce Seed-to-Seed Translation (StS), a novel approach for Image-to-Image Translation using diffusion models (DMs), aimed at translations that require close adherence to the structure of the source image. In contrast to existing…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Or Greenberg , Eran Kishon , Dani Lischinski

While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references,…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Yusuf Dalva , Guocheng Gordon Qian , Maya Goldenberg , Tsai-Shien Chen , Kfir Aberman , Sergey Tulyakov , Pinar Yanardag , Kuan-Chieh Jackson Wang

Visual generative AI models often encounter challenges related to text-image alignment and reasoning limitations. This paper presents a novel method for selectively enhancing the signal at critical denoising steps, optimizing image…

计算机视觉与模式识别 · 计算机科学 2025-04-25 Paul Grimal , Hervé Le Borgne , Olivier Ferret

3D asset generation is getting massive amounts of attention, inspired by the recent success of text-guided 2D content creation. Existing text-to-3D methods use pretrained text-to-image diffusion models in an optimization problem or…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Lukas Höllein , Aljaž Božič , Norman Müller , David Novotny , Hung-Yu Tseng , Christian Richardt , Michael Zollhöfer , Matthias Nießner

Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions. Yet, these models often struggle with interpreting spatial arrangements…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Jiaqi Liu , Tao Huang , Chang Xu

Recently, diffusion-based image generation methods are credited for their remarkable text-to-image generation capabilities, while still facing challenges in accurately generating multilingual scene text images. To tackle this problem, we…

计算机视觉与模式识别 · 计算机科学 2023-12-20 Lingjun Zhang , Xinyuan Chen , Yaohui Wang , Yue Lu , Yu Qiao

Building on recent advances in image generation, we present a fully data-driven approach to rendering markup into images. The approach is based on diffusion models, which parameterize the distribution of data using a sequence of denoising…

机器学习 · 计算机科学 2022-10-12 Yuntian Deng , Noriyuki Kojima , Alexander M. Rush

We consider the problem of conditional text-to-image synthesis with diffusion models. Most recent works need to either finetune specific parts of the base diffusion model or introduce new trainable parameters, leading to deployment…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Tripti Shukla , Srikrishna Karanam , Balaji Vasan Srinivasan

Large text-guided diffusion models, such as DALLE-2, are able to generate stunning photorealistic images given natural language descriptions. While such models are highly flexible, they struggle to understand the composition of certain…

计算机视觉与模式识别 · 计算机科学 2023-01-18 Nan Liu , Shuang Li , Yilun Du , Antonio Torralba , Joshua B. Tenenbaum

Diffusion models have emerged as a promising approach for text generation, with recent works falling into two main categories: discrete and continuous diffusion models. Discrete diffusion models apply token corruption independently using…

计算与语言 · 计算机科学 2025-05-29 Bocheng Li , Zhujin Gao , Linli Xu

Recent progress in text-to-image (TTI) systems, such as StableDiffusion, Imagen, and DALL-E 2, have made it possible to create realistic images with simple text prompts. It is tempting to use these systems to eliminate the manual task of…

计算机视觉与模式识别 · 计算机科学 2023-11-02 David Marwood , Shumeet Baluja , Yair Alon

Text-to-Image (T2I) generation methods based on diffusion model have garnered significant attention in the last few years. Although these image synthesis methods produce visually appealing results, they frequently exhibit spelling errors…

计算机视觉与模式识别 · 计算机科学 2023-12-27 Yiming Zhao , Zhouhui Lian

Recent advances in text-to-image generators have led to substantial capabilities in image generation. However, the complexity of prompts acts as a bottleneck in the quality of images generated. A particular under-explored facet is the…

计算机视觉与模式识别 · 计算机科学 2023-11-27 Tham Yik Foong , Shashank Kotyan , Po Yuan Mao , Danilo Vasconcellos Vargas

Background: Text-to-image generation models are widely used across numerous domains. Among these models, Stable Diffusion (SD) - an open-source text-to-image generation model - has become the most popular, producing over 12 billion images…

软件工程 · 计算机科学 2025-12-08 Giordano d'Aloisio , Tosin Fadahunsi , Jay Choy , Rebecca Moussa , Federica Sarro

Restoring low-resolution text images presents a significant challenge, as it requires maintaining both the fidelity and stylistic realism of the text in restored images. Existing text image restoration methods often fall short in hard…

计算机视觉与模式识别 · 计算机科学 2025-06-17 Chenglu Pan , Xiaogang Xu , Ganggui Ding , Yunke Zhang , Wenbo Li , Jiarong Xu , Qingbiao Wu

Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches. Yet, one pain point persists: the text prompt engineering,…

计算机视觉与模式识别 · 计算机科学 2023-06-02 Xingqian Xu , Jiayi Guo , Zhangyang Wang , Gao Huang , Irfan Essa , Humphrey Shi