中文
相关论文

相关论文: Vision-guided and Mask-enhanced Adaptive Denoising…

200 篇论文

Recently large-scale language-image models (e.g., text-guided diffusion models) have considerably improved the image generation capabilities to generate photorealistic images in various domains. Based on this success, current image editing…

计算机视觉与模式识别 · 计算机科学 2023-05-09 Wenkai Dong , Song Xue , Xiaoyue Duan , Shumin Han

Text-guided image editing model has achieved great success in general domain. However, directly applying these models to the fashion domain may encounter two issues: (1) Inaccurate localization of editing region; (2) Weak editing magnitude.…

计算机视觉与模式识别 · 计算机科学 2025-01-16 Zechao Zhan , Dehong Gao , Jinxia Zhang , Jiale Huang , Yang Hu , Xin Wang

Diffusion-based image editing is a composite process of preserving the source image content and generating new content or applying modifications. While current editing approaches have made improvements under text guidance, most of them have…

计算机视觉与模式识别 · 计算机科学 2024-03-18 Tianrui Huang , Pu Cao , Lu Yang , Chun Liu , Mengjie Hu , Zhiwei Liu , Qing Song

Natural language offers a highly intuitive interface for image editing. In this paper, we introduce the first solution for performing local (region-based) edits in generic natural images, based on a natural language description along with…

计算机视觉与模式识别 · 计算机科学 2023-03-22 Omri Avrahami , Dani Lischinski , Ohad Fried

Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned…

计算机视觉与模式识别 · 计算机科学 2022-10-21 Guillaume Couairon , Jakob Verbeek , Holger Schwenk , Matthieu Cord

Text-to-image (T2I) diffusion models, with their impressive generative capabilities, have been adopted for image editing tasks, demonstrating remarkable efficacy. However, due to attention leakage and collision between the cross-attention…

计算机视觉与模式识别 · 计算机科学 2025-05-01 Xingxi Yin , Zhi Li , Jingfeng Zhang , Chenglin Li , Yin Zhang

Text-guided image editing finds applications in various creative and practical fields. While recent studies in image generation have advanced the field, they often struggle with the dual challenges of coherent image transformation and…

计算机视觉与模式识别 · 计算机科学 2024-12-18 Rumeysa Bodur , Binod Bhattarai , Tae-Kyun Kim

Text-to-image generative models have attracted rising attention for flexible image editing via user-specified descriptions. However, text descriptions alone are not enough to elaborate the details of subjects, often compromising the…

计算机视觉与模式识别 · 计算机科学 2023-06-14 Xin Zhang , Jiaxian Guo , Paul Yoo , Yutaka Matsuo , Yusuke Iwasawa

Recent advancements in text-guided image editing have achieved notable success by leveraging natural language prompts for fine-grained semantic control. However, certain editing semantics are challenging to specify precisely using textual…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Haoguang Lu , Jiacheng Chen , Zhenguo Yang , Aurele Tohokantche Gnanha , Fu Lee Wang , Li Qing , Xudong Mao

Language has emerged as a natural interface for image editing. In this paper, we introduce a method for region-based image editing driven by textual prompts, without the need for user-provided masks or sketches. Specifically, our approach…

计算机视觉与模式识别 · 计算机科学 2024-04-04 Yuanze Lin , Yi-Wen Chen , Yi-Hsuan Tsai , Lu Jiang , Ming-Hsuan Yang

Textual prompt tuning has demonstrated significant performance improvements in adapting natural language processing models to a variety of downstream tasks by treating hand-engineered prompts as trainable parameters. Inspired by the success…

计算机视觉与模式识别 · 计算机科学 2023-09-28 Jiachen Sun , Mark Ibrahim , Melissa Hall , Ivan Evtimov , Z. Morley Mao , Cristian Canton Ferrer , Caner Hazirbas

Editing images using natural language instructions has become a natural and expressive way to modify visual content; yet, evaluating the performance of such models remains challenging. Existing evaluation approaches often rely on image-text…

计算机视觉与模式识别 · 计算机科学 2025-07-28 Yusu Qian , Jiasen Lu , Tsu-Jui Fu , Xinze Wang , Chen Chen , Yinfei Yang , Wenze Hu , Zhe Gan

Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision…

计算机视觉与模式识别 · 计算机科学 2023-01-31 Kun Yi , Yixiao Ge , Xiaotong Li , Shusheng Yang , Dian Li , Jianping Wu , Ying Shan , Xiaohu Qie

Visual-prompt-guided edit transfer aims to learn image transformations directly from example pairs, offering more precise and controllable editing than purely text-driven approaches. However, existing diffusion transformer-based methods…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Lan Chen , Qi Mao , Yiren Song , Yuchao Gu , Siwei Ma

We present EditP23, a method for mask-free 3D editing that propagates 2D image edits to multi-view representations in a 3D-consistent manner. In contrast to traditional approaches that rely on text-based prompting or explicit spatial masks,…

图形学 · 计算机科学 2025-06-26 Roi Bar-On , Dana Cohen-Bar , Daniel Cohen-Or

Segmenting images is critical for visual understanding but demands extensive pixel-level annotations. Foundational models have enabled new paradigms for predicting new classes guided by textual prompts, without annotations from the target…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Gabriele Rosi , Fabio Cermelli , Carlo Masone , Barbara Caputo

Despite significant advancements in image customization with diffusion models, current methods still have several limitations: 1) unintended changes in non-target areas when regenerating the entire image; 2) guidance solely by a reference…

计算机视觉与模式识别 · 计算机科学 2024-07-08 Pengzhi Li , Qiang Nie , Ying Chen , Xi Jiang , Kai Wu , Yuhuan Lin , Yong Liu , Jinlong Peng , Chengjie Wang , Feng Zheng

Diffusion-based point editing methods have gained significant traction in image editing tasks due to their ability to manipulate image semantics and fine details by applying localized perturbations on the manifold of noise latent. However,…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Haoyang Hu , Masataka Seo , Yen-Wei Chen

In computer vision, Visual Prompting (VP) and Visual Prompt Tuning (VPT) have recently emerged as lightweight and effective alternatives to full fine-tuning for adapting large-scale vision models within the "pretrain-then-finetune"…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Xi Xiao , Yunbei Zhang , Lin Zhao , Yiyang Liu , Xiaoying Liao , Zheda Mai , Xingjian Li , Xiao Wang , Hao Xu , Jihun Hamm , Xue Lin , Min Xu , Qifan Wang , Tianyang Wang , Cheng Han

Text-guided image editing aims to modify specific regions according to the target prompt while preserving the identity of the source image. Recent methods exploit explicit binary masks to constrain editing, but hard mask boundaries…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Yongwen Lai , Chaoqun Wang , Shaobo Min