中文
相关论文

相关论文: Improving Multi-Subject Consistency in Open-Domain…

200 篇论文

Text-to-image models offer a new level of creative flexibility by allowing users to guide the image generation process through natural language. However, using these models to consistently portray the same subject across diverse prompts…

计算机视觉与模式识别 · 计算机科学 2024-05-31 Yoad Tewel , Omri Kaduri , Rinon Gal , Yoni Kasten , Lior Wolf , Gal Chechik , Yuval Atzmon

Data imputation and data generation have important applications for many domains, like healthcare and finance, where incomplete or missing data can hinder accurate analysis and decision-making. Diffusion models have emerged as powerful…

机器学习 · 计算机科学 2025-06-10 Mario Villaizán-Vallelado , Matteo Salvatori , Carlos Segura , Ioannis Arapakis

Diffusion models gain increasing popularity for their generative capabilities. Recently, there have been surging needs to generate customized images by inverting diffusion models from exemplar images, and existing inversion methods mainly…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Ziqi Huang , Tianxing Wu , Yuming Jiang , Kelvin C. K. Chan , Ziwei Liu

As pre-trained text-to-image diffusion models have become a useful tool for image synthesis, people want to specify the results in various ways. This paper tackles training-free appearance transfer, which produces an image with the…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Sooyeon Go , Kyungmook Choi , Minjung Shin , Youngjung Uh

The In-context generation paradigm recently has demonstrated strong power in instructional image editing with both data efficiency and synthesis quality. Nevertheless, shaping such in-context learning for instruction-based video editing is…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Zhongwei Zhang , Fuchen Long , Wei Li , Zhaofan Qiu , Wu Liu , Ting Yao , Tao Mei

While large-scale text-to-image diffusion models enable the generation of high-quality, diverse images from text prompts, these prompts struggle to capture intricate details, such as textures, preventing the user intent from being…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Kyungmin Jo , Jooyeol Yun , Jaegul Choo

Current subject-driven image generation methods encounter significant challenges in person-centric image generation. The reason is that they learn the semantic scene and person generation by fine-tuning a common pre-trained diffusion, which…

计算机视觉与模式识别 · 计算机科学 2024-05-06 Yibin Wang , Weizhong Zhang , Jianwei Zheng , Cheng Jin

Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to perform edits without extensive model adjustments, offering…

计算机视觉与模式识别 · 计算机科学 2024-12-02 Wenyi Mo , Tianyu Zhang , Yalong Bai , Bing Su , Ji-Rong Wen

Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Jiexuan Zhang , Yiheng Du , Qian Wang , Weiqi Li , Yu Gu , Jian Zhang

Recent prosperity of text-to-image diffusion models, e.g. Stable Diffusion, has stimulated research to adapt them to 360-degree panorama generation. Prior work has demonstrated the feasibility of using conventional low-rank adaptation…

计算机视觉与模式识别 · 计算机科学 2025-05-29 Jinhong Ni , Chang-Bin Zhang , Qiang Zhang , Jing Zhang

Image restoration (IR) has been an indispensable and challenging task in the low-level vision field, which strives to improve the subjective quality of images distorted by various forms of degradation. Recently, the diffusion model has…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Xin Li , Yulin Ren , Xin Jin , Cuiling Lan , Xingrui Wang , Wenjun Zeng , Xinchao Wang , Zhibo Chen

Most of the existing Zero-Shot Learning (ZSL) methods focus on learning a compatibility function between the image representation and class attributes. Few others concentrate on learning image representation combining local and global…

计算机视觉与模式识别 · 计算机科学 2021-10-05 Faisal Alamri , Anjan Dutta

Recent advances in diffusion models have enhanced multimodal-guided visual generation, enabling customized subject insertion that seamlessly "brushes" user-specified objects into a given image guided by textual prompts. However, existing…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Yu Xu , Fan Tang , You Wu , Lin Gao , Oliver Deussen , Hongbin Yan , Jintao Li , Juan Cao , Tong-Yee Lee

Multi-subject image generation aims to synthesize user-provided subjects in a single image while preserving subject fidelity, ensuring prompt consistency, and aligning with human aesthetic preferences. Existing In-Context-Learning based…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Tao Wu , Yibo Jiang , Yehao Lu , Zhizhong Wang , Zeyi Huang , Zequn Qin , Xi Li

Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a passive and under-optimized byproduct. This imbalance compromises global scene coherence and…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Yang Deng , David Mould , Paul L. Rosin , Yu-Kun Lai

We present ControlSR, a new method that can tame Diffusion Models for consistent real-world image super-resolution (Real-ISR). Previous Real-ISR models mostly focus on how to activate more generative priors of text-to-image diffusion models…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Yuhao Wan , Peng-Tao Jiang , Qibin Hou , Hao Zhang , Jinwei Chen , Ming-Ming Cheng , Bo Li

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy.…

计算机视觉与模式识别 · 计算机科学 2023-08-15 David Junhao Zhang , Mutian Xu , Chuhui Xue , Wenqing Zhang , Xiaoguang Han , Song Bai , Mike Zheng Shou

Modern agricultural operations increasingly rely on integrated monitoring systems that combine multiple data sources for farm optimization. Aerial drone-based animal health monitoring serves as a key component but faces limited data…

计算机视觉与模式识别 · 计算机科学 2026-01-20 Nisha Pillai

This paper presents innovative enhancements to diffusion models by integrating a novel multi-resolution network and time-dependent layer normalization. Diffusion models have gained prominence for their effectiveness in high-fidelity image…

计算机视觉与模式识别 · 计算机科学 2024-12-02 Qihao Liu , Zhanpeng Zeng , Ju He , Qihang Yu , Xiaohui Shen , Liang-Chieh Chen

Images generated by diffusion models like Stable Diffusion are increasingly widespread. Recent works and even lawsuits have shown that these models are prone to replicating their training data, unbeknownst to the user. In this paper, we…

机器学习 · 计算机科学 2023-06-01 Gowthami Somepalli , Vasu Singla , Micah Goldblum , Jonas Geiping , Tom Goldstein