中文
相关论文

相关论文: Large-Scale Text-to-Image Model with Inpainting is…

200 篇论文

Recent innovations on text-to-3D generation have featured Score Distillation Sampling (SDS), which enables the zero-shot learning of implicit 3D models (NeRF) by directly distilling prior knowledge from 2D diffusion models. However, current…

计算机视觉与模式识别 · 计算机科学 2024-03-26 Yang Chen , Yingwei Pan , Haibo Yang , Ting Yao , Tao Mei

Advancing image inpainting is challenging as it requires filling user-specified regions for various intents, such as background filling and object synthesis. Existing approaches focus on either context-aware filling or object synthesis…

计算机视觉与模式识别 · 计算机科学 2024-07-24 Junhao Zhuang , Yanhong Zeng , Wenran Liu , Chun Yuan , Kai Chen

Subject-driven text-to-image generation aims to generate customized images of the given subject based on the text descriptions, which has drawn increasing attention. Existing methods mainly resort to finetuning a pretrained generative…

计算机视觉与模式识别 · 计算机科学 2024-02-28 Hong Chen , Yipeng Zhang , Simin Wu , Xin Wang , Xuguang Duan , Yuwei Zhou , Wenwu Zhu

Despite the burst of innovative methods for controlling the diffusion process, effectively controlling image styles in text-to-image generation remains a challenging task. Many adapter-based methods impose image representation conditions on…

计算机视觉与模式识别 · 计算机科学 2024-09-05 Wen Li , Muyuan Fang , Cheng Zou , Biao Gong , Ruobing Zheng , Meng Wang , Jingdong Chen , Ming Yang

The excellent generative capabilities of text-to-image diffusion models suggest they learn informative representations of image-text data. However, what knowledge their representations capture is not fully understood, and they have not been…

计算机视觉与模式识别 · 计算机科学 2023-09-07 Kevin Clark , Priyank Jaini

Text-to-image generative models have demonstrated remarkable capabilities in generating high-quality images based on textual prompts. However, crafting prompts that accurately capture the user's creative intent remains challenging. It often…

人机交互 · 计算机科学 2023-04-20 Stephen Brade , Bryan Wang , Mauricio Sousa , Sageev Oore , Tovi Grossman

Text-to-image generative models often struggle with long prompts detailing complex scenes, diverse objects with distinct visual characteristics and spatial relationships. In this work, we propose SCoPE (Scheduled interpolation of…

计算机视觉与模式识别 · 计算机科学 2025-06-02 Ketan Suhaas Saichandran , Xavier Thomas , Prakhar Kaushik , Deepti Ghadiyaram

Image caption generation is a long standing and challenging problem at the intersection of computer vision and natural language processing. A number of recently proposed approaches utilize a fully supervised object recognition model within…

计算机视觉与模式识别 · 计算机科学 2019-08-02 Berkan Demirel , Ramazan Gokberk Cinbis , Nazli Ikizler-Cinbis

Building on the success of text-to-image diffusion models (DPMs), image editing is an important application to enable human interaction with AI-generated content. Among various editing methods, editing within the prompt space gains more…

计算机视觉与模式识别 · 计算机科学 2025-01-28 Aosong Feng , Weikang Qiu , Jinbin Bai , Xiao Zhang , Zhen Dong , Kaicheng Zhou , Rex Ying , Leandros Tassiulas

Text-to-image generation models are powerful but difficult to use. Users craft specific prompts to get better images, though the images can be repetitive. This paper proposes a Prompt Expansion framework that helps users generate…

计算机视觉与模式识别 · 计算机科学 2023-12-29 Siddhartha Datta , Alexander Ku , Deepak Ramachandran , Peter Anderson

Semantic image inpainting is a challenging task where large missing regions have to be filled based on the available visual data. Existing methods which extract information from only a single image generally produce unsatisfactory results…

计算机视觉与模式识别 · 计算机科学 2017-07-14 Raymond A. Yeh , Chen Chen , Teck Yian Lim , Alexander G. Schwing , Mark Hasegawa-Johnson , Minh N. Do

Reference-based object composition involves integrating foreground reference image with background scene to produce harmonious fused image. This task becomes particularly challenging in cross-domain scenarios, where models must balance…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Raghu Vamsi Chittersu , Yuvraj Singh Rathore , Pranav Adlinge , Kunal Swami

Text-to-image models have shown remarkable progress in generating high-quality images from user-provided prompts. Despite this, the quality of these images varies due to the models' sensitivity to human language nuances. With advancements…

人工智能 · 计算机科学 2024-06-14 Xinrui Yang , Zhuohan Wang , Anthony Hu

Generating multiple distinct subjects remains a challenge for existing text-to-image diffusion models. Complex prompts often lead to subject leakage, causing inaccuracies in quantities, attributes, and visual features. Preventing leakage…

计算机视觉与模式识别 · 计算机科学 2025-05-28 Omer Dahary , Yehonathan Cohen , Or Patashnik , Kfir Aberman , Daniel Cohen-Or

Recent advancements in Text-to-Image (T2I) diffusion models have demonstrated impressive success in generating high-quality images with zero-shot generalization capabilities. Yet, current models struggle to closely adhere to prompt…

计算机视觉与模式识别 · 计算机科学 2024-01-31 Hyun Kang , Dohae Lee , Myungjin Shin , In-Kwon Lee

Recent advances in text-to-image diffusion models have substantially improved the quality of image customization, enabling the synthesis of highly realistic images. Despite this progress, achieving fast and efficient personalization remains…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Aniket Roy , Maitreya Suin , Rama Chellappa

The notable gap between user-provided and model-preferred prompts poses a significant challenge for generating high-quality images with text-to-image models, compelling the need for prompt engineering. Current studies on prompt engineering…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Shiyu Wu , Mingzhen Sun , Weining Wang , Yequan Wang , Jing Liu

Text-to-image generation model is able to generate images across a diverse range of subjects and styles based on a single prompt. Recent works have proposed a variety of interaction methods that help users understand the capabilities of…

人机交互 · 计算机科学 2023-07-19 Seungho Baek , Hyerin Im , Jiseung Ryu , Juhyeong Park , Takyeon Lee

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…

计算机视觉与模式识别 · 计算机科学 2024-04-05 Kaixin Zhang , Zhixiang Yuan , Tao Huang

In the evolving domain of text-to-image generation, diffusion models have emerged as powerful tools in content creation. Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a…

计算机视觉与模式识别 · 计算机科学 2024-02-22 Jaeseok Jeong , Junho Kim , Yunjey Choi , Gayoung Lee , Youngjung Uh