中文
相关论文

相关论文: Glaze: Protecting Artists from Style Mimicry by Te…

200 篇论文

Despite nearly a decade of literature on style transfer, there is no undisputed definition of artistic style. State-of-the-art models produce impressive results but are difficult to interpret since, without a coherent definition of style,…

计算机视觉与模式识别 · 计算机科学 2024-12-06 Emma Finn , T. Anderson Keller , Emmanouil Theodosis , Demba E. Ba

This paper explores the task of detecting images generated by text-to-image diffusion models. To evaluate this, we consider images generated from captions in the MSCOCO and Wikimedia datasets using two state-of-the-art models: Stable…

计算机视觉与模式识别 · 计算机科学 2023-04-24 Davide Alessandro Coccomini , Andrea Esuli , Fabrizio Falchi , Claudio Gennaro , Giuseppe Amato

Generative text-to-image models are typically trained on large-scale web-scraped datasets that include diverse visual content such as copyrighted and stylistically distinctive artworks, raising concerns about ownership, attribution, and the…

机器学习 · 计算机科学 2026-05-19 Ninad Joshi , Ashutosh Ranjan , Vivek Srivastava , Shirish Karande

Text-to-image diffusion models allow seamless generation of personalized images from scant reference photos. Yet, these tools, in the wrong hands, can fabricate misleading or harmful content, endangering individuals. To address this…

计算机视觉与模式识别 · 计算机科学 2024-04-30 Yixin Liu , Chenrui Fan , Yutong Dai , Xun Chen , Pan Zhou , Lichao Sun

Diffusion models have recently been shown to generate high-quality synthetic images, especially when paired with a guidance technique to trade off diversity for fidelity. We explore diffusion models for the problem of text-conditional image…

计算机视觉与模式识别 · 计算机科学 2022-03-09 Alex Nichol , Prafulla Dhariwal , Aditya Ramesh , Pranav Shyam , Pamela Mishkin , Bob McGrew , Ilya Sutskever , Mark Chen

Cutting-edge diffusion models produce images with high quality and customizability, enabling them to be used for commercial art and graphic design purposes. But do diffusion models create unique works of art, or are they replicating content…

机器学习 · 计算机科学 2022-12-13 Gowthami Somepalli , Vasu Singla , Micah Goldblum , Jonas Geiping , Tom Goldstein

Text-to-image diffusion models can be fine-tuned in custom domains to adapt to specific user preferences, but such adaptability has also been utilized for illegal purposes, such as forging public figures' portraits, duplicating copyrighted…

机器学习 · 计算机科学 2024-11-28 Kai Huang , Haoming Wang , Wei Gao

Text-conditioned diffusion models can generate impressive images, but fall short when it comes to fine-grained control. Unlike direct-editing tools like Photoshop, text conditioned models require the artist to perform "prompt engineering,"…

计算机视觉与模式识别 · 计算机科学 2024-04-05 Michelle Shu , Charles Herrmann , Richard Strong Bowen , Forrester Cole , Ramin Zabih

Taking advantage of the many recent advances in deep learning, text-to-image generative models currently have the merit of attracting the general public attention. Two of these models, DALL-E 2 and Imagen, have demonstrated that highly…

计算机视觉与模式识别 · 计算机科学 2022-09-23 Robin Zbinden

Synthesizing visually impressive images that seamlessly align both text prompts and specific artistic styles remains a significant challenge in Text-to-Image (T2I) diffusion models. This paper introduces StyleBlend, a method designed to…

计算机视觉与模式识别 · 计算机科学 2025-02-14 Zichong Chen , Shijin Wang , Yang Zhou

Building generic robotic manipulation systems often requires large amounts of real-world data, which can be dificult to collect. Synthetic data generation offers a promising alternative, but limiting the sim-to-real gap requires significant…

机器人学 · 计算机科学 2024-11-18 Thomas Lips , Francis wyffels

Generative text-to-image models are disrupting the lives of creative professionals. Specifically, illustrators are threatened by models that claim to extract and reproduce their style. Yet, research on style transfer has rarely focused on…

人机交互 · 计算机科学 2025-01-31 Julien Porquet , Sitong Wang , Lydia B. Chilton

Recent image protection mechanisms such as Glaze and Nightshade introduce imperceptible, adversarially designed perturbations intended to disrupt downstream text-to-image generative models. While their empirical effectiveness is known, the…

计算机视觉与模式识别 · 计算机科学 2025-12-10 Michael R. Martin , Garrick Chan , Kwan-Liu Ma

Diffusion models have demonstrated exceptional capabilities in generating a broad spectrum of visual content, yet their proficiency in rendering text is still limited: they often generate inaccurate characters or words that fail to blend…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Jianyi Zhang , Yufan Zhou , Jiuxiang Gu , Curtis Wigington , Tong Yu , Yiran Chen , Tong Sun , Ruiyi Zhang

Given a style-reference image as the additional image condition, text-to-image diffusion models have demonstrated impressive capabilities in generating images that possess the content of text prompts while adopting the visual style of the…

计算机视觉与模式识别 · 计算机科学 2025-02-12 Lin Zhu , Xinbing Wang , Chenghu Zhou , Qinying Gu , Nanyang Ye

Personalized text-to-image models allow users to generate images of new concepts from several reference photos, thereby leading to critical concerns regarding civil privacy. Although several anti-personalization techniques have been…

计算机视觉与模式识别 · 计算机科学 2025-02-13 Qianrui Teng , Xing Cui , Xuannan Liu , Peipei Li , Zekun Li , Huaibo Huang , Ran He

Humans can infer material characteristics of objects from their visual appearance, and this ability extends to artistic depictions, where similar perceptual strategies guide the interpretation of paintings or drawings. Among the factors…

图形学 · 计算机科学 2026-02-20 Santiago Jimenez-Navarro , Belen Masia , Ana Serrano

Recent advances in latent diffusion models have enabled exciting progress in image style transfer. However, several key issues remain. For example, existing methods still struggle to accurately match styles. They are often limited in the…

计算机视觉与模式识别 · 计算机科学 2025-08-19 Dan Ruta , Abdelaziz Djelouah , Raphael Ortiz , Christopher Schroers

Text-to-Image artificial intelligence (AI) recently saw a major breakthrough with the release of Dall-E and its open-source counterpart, Stable Diffusion. These programs allow anyone to create original visual art pieces by simply providing…

人机交互 · 计算机科学 2023-01-06 Nassim Dehouche , Kullathida Dehouche

Generative models have enabled intuitive image creation and manipulation using natural language. In particular, diffusion models have recently shown remarkable results for natural image editing. In this work, we propose to apply diffusion…