中文
相关论文

相关论文: DECOR:Decomposition and Projection of Text Embeddi…

200 篇论文

The quality of the prompts provided to text-to-image diffusion models determines how faithful the generated content is to the user's intent, often requiring `prompt engineering'. To harness visual concepts from target images without prompt…

计算机视觉与模式识别 · 计算机科学 2023-12-20 Shweta Mahajan , Tanzila Rahman , Kwang Moo Yi , Leonid Sigal

Image colorization has been attracting the research interests of the community for decades. However, existing methods still struggle to provide satisfactory colorized results given grayscale images due to a lack of human-like global…

计算机视觉与模式识别 · 计算机科学 2023-04-24 Hanyuan Liu , Jinbo Xing , Minshan Xie , Chengze Li , Tien-Tsin Wong

Large language models can deceive by subtly manipulating truthful information -- omitting key facts, shifting focus, or obscuring meaning -- making such behavior difficult to detect. Existing black-box methods rely on coarse-grained…

计算与语言 · 计算机科学 2026-05-20 Linyue Cai , Samuel Yeh , Jwala Dhamala , Rahul Gupta , Sharon Li

The success of recent text-to-image diffusion models is largely due to their capacity to be guided by a complex text prompt, which enables users to precisely describe the desired content. However, these models struggle to effectively…

计算机视觉与模式识别 · 计算机科学 2024-02-09 Senmao Li , Joost van de Weijer , Taihang Hu , Fahad Shahbaz Khan , Qibin Hou , Yaxing Wang , Jian Yang

Text-to-Image (T2I) has been prevalent in recent years, with most common condition tasks having been optimized nicely. Besides, counterfactual Text-to-Image is obstructing us from a more versatile AIGC experience. For those scenes that are…

计算机视觉与模式识别 · 计算机科学 2025-05-21 Sifan Li , Ming Tao , Hao Zhao , Ling Shao , Hao Tang

Large-scale, pre-trained Text-to-Image (T2I) diffusion models have gained significant popularity in image generation tasks and have shown unexpected potential in image Super-Resolution (SR). However, most existing T2I diffusion models are…

计算机视觉与模式识别 · 计算机科学 2024-11-20 Brian B. Moser , Stanislav Frolov , Tobias C. Nauen , Federico Raue , Andreas Dengel

Recent advancements in diffusion models trained on large-scale data have enabled the generation of indistinguishable human-level images, yet they often produce harmful content misaligned with human values, e.g., social bias, and offensive…

计算机视觉与模式识别 · 计算机科学 2024-10-17 Xingqi Wang , Xiaoyuan Yi , Xing Xie , Jia Jia

The objective of personalization and stylization in text-to-image is to instruct a pre-trained diffusion model to analyze new concepts introduced by users and incorporate them into expected styles. Recently, parameter-efficient fine-tuning…

计算机视觉与模式识别 · 计算机科学 2024-03-13 Likun Li , Haoqi Zeng , Changpeng Yang , Haozhe Jia , Di Xu

Current diversification strategies for text-to-image (T2I) models often ignore contextual appropriateness, leading to over-diversification where demographic attributes are modified even when explicitly specified in prompts. This paper…

计算与语言 · 计算机科学 2025-07-11 Felix Friedrich , Thiemo Ganesha Welsch , Manuel Brack , Patrick Schramowski , Kristian Kersting

Personalized text-to-image generation has attracted unprecedented attention in the recent few years due to its unique capability of generating highly-personalized images via using the input concept dataset and novel textual prompt. However,…

人工智能 · 计算机科学 2024-07-02 Shian Du , Xiaotian Cheng , Qi Qian , Henglu Wei , Yi Xu , Xiangyang Ji

While diffusion model fine-tuning offers a powerful approach for customizing pre-trained models to generate specific objects, it frequently suffers from overfitting when training samples are limited, compromising both generalization…

计算机视觉与模式识别 · 计算机科学 2026-01-26 Vera Soboleva , Aibek Alanov , Andrey Kuznetsov , Konstantin Sobolev

Recently, we have seen a surge of personalization methods for text-to-image (T2I) diffusion models to learn a concept using a few images. Existing approaches, when used for face personalization, suffer to achieve convincing inversion with…

计算机视觉与模式识别 · 计算机科学 2024-08-12 Rishubh Parihar , Sachidanand VS , Sabariswaran Mani , Tejan Karmali , R. Venkatesh Babu

Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially utilize image inputs, focusing on specific elements like…

计算机视觉与模式识别 · 计算机科学 2025-03-20 Teng-Fang Hsiao , Bo-Kai Ruan , Yi-Lun Wu , Tzu-Ling Lin , Hong-Han Shuai

Diffusion models have demonstrated impressive performance in text-guided image generation. Current methods that leverage the knowledge of these models for image editing either fine-tune them using the input image (e.g., Imagic) or…

计算机视觉与模式识别 · 计算机科学 2023-11-09 Zhongping Zhang , Jian Zheng , Jacob Zhiyuan Fang , Bryan A. Plummer

The goal of image composition is merging a foreground object into a background image to obtain a realistic composite image. Recently, generative composition methods are built on large pretrained diffusion models, due to their unprecedented…

计算机视觉与模式识别 · 计算机科学 2024-01-25 Lingxiao Lu , Jiangtong Li , Bo Zhang , Li Niu

In this report, we explore the potential for text diffusion to replace autoregressive (AR) decoding for the training and deployment of large language models (LLMs). We are particularly interested to see whether pretrained AR models can be…

计算与语言 · 计算机科学 2024-01-31 Kehang Han , Kathleen Kenealy , Aditya Barua , Noah Fiedel , Noah Constant

Current diffusion models create photorealistic images given a text prompt as input but struggle to correctly bind attributes mentioned in the text to the right objects in the image. This is evidenced by our novel image-graph alignment model…

计算机视觉与模式识别 · 计算机科学 2024-04-23 Maria Mihaela Trusca , Wolf Nuyts , Jonathan Thomm , Robert Honig , Thomas Hofmann , Tinne Tuytelaars , Marie-Francine Moens

Recent progress in text-to-image (T2I) models enables high-quality image generation with flexible textual control. To utilize the abundant visual priors in the off-the-shelf T2I models, a series of methods try to invert an image to proper…

计算机视觉与模式识别 · 计算机科学 2023-10-13 Zijie Wu , Chaohui Yu , Zhen Zhu , Fan Wang , Xiang Bai

Recent text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images given text-prompts as input. However, these models fail to convey appropriate spatial composition specified by a layout…

计算机视觉与模式识别 · 计算机科学 2023-11-28 Jiayu Xiao , Henglei Lv , Liang Li , Shuhui Wang , Qingming Huang

Groundbreaking advancements in text-to-image generation have recently been achieved with the emergence of diffusion models. These models exhibit a remarkable ability to generate highly artistic and intricately detailed images based on…

计算机视觉与模式识别 · 计算机科学 2025-02-10 Ziyi Dong , Yao Xiao , Pengxu Wei , Liang Lin