检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhan, Zechao Gao, Dehong Zhang, Jinxia Huang, Jiale Hu, Yang Wang, Xin Key Laboratory of Measurement and Control of CSE Ministry of Education School of Automation Southeast University Nanjing210096 China Advanced Ocean Institute Southeast University Nantong226010 China Northwestern Polytechnical University School of Cybersecurity Xi'an China Binjiang Institute of Artificial Intelligence ZJUT Hangzhou China Alibaba Group Hangzhou China

ISBN: (纸本)9798350368741

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. To address these issues, the MADiff model is proposed. Specifically, to more accurately identify editing region, the MaskNet is proposed, in which the foreground region, densepose and mask prompts from large language model are fed into a lightweight UNet to predict the mask for editing region. To strengthen the editing magnitude, the Attention-Enhanced Diffusion Model is proposed, where the noise map, attention map, and the mask from MaskNet are fed into the proposed Attention Processor to produce a refined noise map. By integrating the refined noise map into the diffusion model, the edited image can better align with the target prompt. Given the absence of benchmarks in fashion image editing, we constructed a dataset named Fashion-E, comprising 28390 image-text pairs in the training set, and 2639 image-text pairs for four types of fashion tasks in the evaluation set. Extensive experiments on Fashion-E demonstrate that our proposed method can accurately predict the mask of editing region and significantly enhance editing magnitude in fashion image editing compared to the state-of-the-art methods. © 2025 IEEE.

关键词： Diffusion Model Fashion Domain text-guided image editing

来源：评论

学校读者我要写书评

暂无评论

MFECLIP: CLIP With Mapping-Fusion Embedding for text-guided image editing

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 116-120页

作者： Wu, Fei Ma, Yongheng Jin, Hao Jing, Xiao-Yuan Jiang, Guo-Ping Nanjing Univ Posts & Telecommun Coll Automat Nanjing 210049 Peoples R China Nanjing Univ Posts & Telecommun Coll Artificial Intelligence Nanjing 210049 Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China

Recently, generative adversarial networks (GAN) have made remarkable progress, particularly with the advent of Contrastive Language-image Pretraining (CLIP), which take image and text into a joint latent space, bridging the gap between these two modalities. Several impressive text-guided image editing methods based on GANs and CLIP have emerged. However, in these studies, most of them simply minimize the distance between the target image embedding and text embedding in the CLIP space, and take this objective as network's optimization goal, overlooking the real distance between them may be large. This may result in inability to accurately guide the editing process according to the text prompts and the changes in text-irrelevant attributes. To mitigate this issue, we propose a novel approach named CLIP with Mapping-Fusion Embedding (MFECLIP) for text-guided image editing, which comprises two components: the MFE Block and MFE Loss. Through the MFE Block, we obtain Mapping-Fusion Embedding (MFE), which can further eliminate the modality gap, and it can serve as a superior guide for editing process instead of the original text embedding. Based on contrastive learning, the MFE Loss is designed to achieve accurate alignment between the target image and text prompt. We have conducted extensive experiments on real datasets, CUB and Oxford, demonstrating the favorable performance of the proposed method.

关键词： Semantics Generative adversarial networks Training Task analysis Flowering plants Birds Telecommunications text-guided image editing GAN CLIP

来源：评论

学校读者我要写书评

暂无评论

text-guided image editing Based on Post Score for Gaining Attention on Social Media

引用

SENSORS 2024年第3期24卷 921-921页

作者： Watanabe, Yuto Togo, Ren Maeda, Keisuke Ogawa, Takahiro Haseyama, Miki Hokkaido Univ Grad Sch Informat Sci & Technol N-14W-9Kita Ku Sapporo Hokkaido 0600814 Japan Hokkaido Univ Fac Informat Sci & Technol N-14W-9Kita Ku Sapporo Hokkaido 0600814 Japan

text-guided image editing has been highlighted in the fields of computer vision and natural language processing in recent years. The approach takes an image and text prompt as input and aims to edit the image in accordance with the text prompt while preserving text-unrelated regions. The results of text-guided image editing differ depending on the way the text prompt is represented, even if it has the same meaning. It is up to the user to decide which result best matches the intended use of the edited image. This paper assumes a situation in which edited images are posted to social media and proposes a novel text-guided image editing method to help the edited images gain attention from a greater audience. In the proposed method, we apply the pre-trained text-guided image editing method and obtain multiple edited images from the multiple text prompts generated from a large language model. The proposed method leverages the novel model that predicts post scores representing engagement rates and selects one image that will gain the most attention from the audience on social media among these edited images. Subject experiments on a dataset of real Instagram posts demonstrate that the edited images of the proposed method accurately reflect the content of the text prompts and provide a positive impression to the audience on social media compared to those of previous text-guided image editing methods.

关键词： text-guided image editing diffusion model posted image editing post score social media marketing

来源：评论

学校读者我要写书评

暂无评论

Controlling Attention Map Better for text-guided image editing Diffusion Models 20th

Controlling Attention Map Better for Text-Guided Image Editi...

引用

20th International Conference on Intelligent Computing (ICIC)

作者： Xu, Siqi Sun, Lijun Liu, Guanming Wei, Zhihua Tongji Univ Sch Comp Sci & Technol 4800 Caoan Rd Shanghai Peoples R China

ISBN: (纸本)9789819756148;9789819756155

Large visual-language models such as GLIDE, DALL-E 2, and imagen show remarkable capabilities in image generation. However, applying these models to image editing presents challenges as slight changes to the prompt can lead to vastly different final images. The emergence of text-guided diffusion models is gradually establishing itself as a mainstream technique for image generation due to its realism and versatility. The latent space noise in diffusion models possesses the ability to both preserve and modify the final image. Consequently, an increasing number of methods are employing diffusion models for text-guided image editing by exploring the process of noise generation. Despite the significant progress made by diffusion-based methods in image generation and editing, they often focus on specific application aspects. While these approaches yield outstanding results in their respective domains, there exists a lack of a unified method that integrates different editing approaches. This absence impedes users from choosing an algorithm that best suits their needs. To address this, we propose a convergent attention map modification framework. This framework seamlessly integrates various attention map control methods, allowing for controllable generation through different parameter combinations.

关键词： text-guided image editing text-to-image Generation Diffusion Models

来源：评论

学校读者我要写书评

暂无评论

An Evaluation of text-guided image editing Models 16

An Evaluation of Text-Guided Image Editing Models

引用

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Phong, Nguyen Tien Onuoha, Chibuike Huong, Truong Thu Nam, Pham Ngoc Thang, Truong Cong The University of Aizu Aizuwakamatsu965-8580 Japan VinUniversity Hanoi Viet Nam Hanoi University of Science and Technology Hanoi Viet Nam

ISBN: (纸本)9798331505264

text-guided image editing, which modifies images based solely on an input image and a target text prompt, will soon become a crucial function in computer vision and image processing. However, evaluations of existing models are still very limited. In this study, we systematically evaluate state-of-the-art models for text-guided image editing through both subjective and objective quality assessments, marking the first comprehensive evaluation to address all four essential criteria: Alignment, Preservation, Perception, and Acceptability, with a robust participant base for reliability. This methodology enables an in-depth comparison of models, showing that Imagic and Forgedit consistently lead in all criteria. Furthermore, our objective analysis, utilizing a wide range of image Quality Assessment (IQA) and alignment metrics, reveals significant limitations in the existing metrics' abilities to evaluate accurately the performance of text-guided image editing models. © 2024 IEEE.

关键词： Model Evaluation Objective Metrics Quality assessment text-guided image editing

来源：评论

学校读者我要写书评

暂无评论

TGDrag: Adding Semantic Control into Point-based image editing via text Guidance

TGDrag: Adding Semantic Control into Point-based Image Editi...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Lin, Chenhao Zhu, Yanjie Miao, Yingmao Zhao, Zhengyu Liu, Shuai Shen, Chao Xi'an Jiaotong University China

ISBN: (纸本)9798350368741

Controllable image generation has emerged as a cutting-edge subject of interest. Current interactive point-based image editing frameworks, such as DragGAN, achieve impressive results in fine-grained and controllable image editing. However, relying solely on point-based manipulations can lead to unintended outcomes due to the inherent lack of the users' semantic intent. To address this issue, we introduce text-guided Drag (TGDrag), a novel approach to adding semantic control into point-based image editing by using text prompts to guide the manipulation of handle and target points. Specifically, we design a channel correlation calculator that adaptively selects channels for the text and points to mitigate the potential influence of semantic control on point control. Furthermore, we introduce a text loss function to minimize the discrepancy between the generated images and the text prompts. Experimental results demonstrate that TGDrag achieves the expected function of semantic control while maintaining effectiveness regarding point control. © 2025 IEEE.

关键词： Generative adversarial network Interactive editing Semantic control text-guided image editing

来源：评论

学校读者我要写书评

暂无评论

text-guided Multi-region Scene image editing Based on Diffusion Model 20th

Text-Guided Multi-region Scene Image Editing Based on Diffus...

引用

20th International Conference on Intelligent Computing (ICIC)

作者： Li, Ruichen Wu, Lei Wang, Changshuo Dong, Pei Li, Xin Shandong Univ Jinan Peoples R China

ISBN: (纸本)9789819756117;9789819756124

The tremendous progress in neural image generation, coupled with the emergence of seemingly omnipotent vision-language models have finally enabled text-guided editing realistic scene images. The latest works utilize diffusion models and most studies focus on editing individual regions based on a given text prompt. When the user delineates multiple regions, these models cannot edit in the corresponding areas based on different text semantics. Hence, we propose a new diffusion-based text-guided multi-region scene image editing model, which can handle multiple regions and corresponding text, and focus on entity-level object editing and layout-level background coordination at different denoising steps respectively. At the early steps of the denoising, we propose a mask dilation based object editing method that dilates thinner masks to ensure the accuracy of editing multiple objects. In layout-level background coordination, we not only encourage the noisy version of the original scene image to replace the random noise in the background region in the diffusion reversion process, but also propose Outward Low-pass Filtering (OutwardLPF) to eliminate the sharp transitions of noise levels between edited image regions. We conduct extensive experiments showing that our model outperforms all baselines in terms of multi-object entity editing and background coordination.

关键词： text-guided image editing Diffusion model image manipulation

来源：评论

学校读者我要写书评

暂无评论

MorphNeRF: text-guided 3D-Aware editing via Morphing Generative Neural Radiance Fields

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 8516-8528页

作者： Yu, Yingchen Wu, Rongliang Men, Yifang Lu, Shijian Cui, Miaomiao Xie, Xuansong Miao, Chunyan Nanyang Technol Univ Sch Comp Sci & Engn Singapore 308232 Singapore Nanyang Technol Univ Singapore 308232 Singapore ASTAR Inst Infocomm Res I2R Singapore 138632 Singapore Alibaba Grp Damo Acad Hangzhou 311121 Peoples R China

Generative neural radiance fields (NeRF) bring image generation into the 3D era, which have delivered impressive generation quality and 3D consistency, especially in the face generation domain. Upon pre-trained generative NeRF, 3D-aware image editing has been explored and achieved promising performance via manipulating semantic maps or attributes. However, a more flexible editing interface, text, remains under-explored in the context of 3D-aware image editing. In this work, we leverage the Contrastive Language-image Pre-training (CLIP) model to achieve 3D-aware image editing in pre-trained generative NeRF models given a target text prompt. To achieve accurate and controllable geometry editing, we propose MorphNeRF, a learnable morphing network that morphs the 3D geometry of images toward the target descriptions via generative NeRF. Different from prior studies that achieve image editing by manipulating latent codes or directly finetuning pre-trained models, morphing the geometry can better preserve the texture of the source image and facilitate the control of editing strength by adjusting the weight of morphing maps explicitly. Extensive experiments and comparisons show that the proposed MorphNeRF achieves superior image editing performance.

关键词： Geometry Three-dimensional displays Solid modeling Codes image synthesis Rendering (computer graphics) Deformable models Multimodal neural radiance field text-guided image editing

来源：评论

学校读者我要写书评

暂无评论

GROUNDED-INSTRUCT-PIX2PIX: IMPROVING INSTRUCTION BASED image editing WITH AUTOMATIC TARGET GROUNDING 49

GROUNDED-INSTRUCT-PIX2PIX: IMPROVING INSTRUCTION BASED IMAGE...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shagidanov, Artur Poghosyan, Hayk Gong, Xinyu Wang, Zhangyang Navasardyan, Shant Shi, Humphrey Picsart AI Res PAIR Miami FL 33178 USA UT Austin Austin TX USA Georgia Inst Technol Atlanta GA USA

ISBN: (纸本)9798350344868;9798350344851

text-guided image editing has recently attracted significant attention due to advances in the denoising diffusion models field. Current methods make it possible to execute complex image editing operations with simple text prompts. But despite impressive results, they often fail to restrict the edit area to only the object of interest, specified in the text prompt. To this end, we propose a novel framework we name Grounded-Instruct-Pix2Pix, which is capable of localized instruction-guided image editing in various scenarios including multi-object cases and complex backgrounds. Our experiments on a diverse set of images clearly showcase its advantage over the recent state-of-the-art approaches, especially at restricting the editing effect to the area of interest only. Grounded-Instruct-Pix2Pix implementation will be available at https://***/arthur-71/Grounded-Instruct-Pix2Pix.

关键词： text-guided image editing deep generative models machine learning

来源：评论

学校读者我要写书评

暂无评论

SAMControl: Controlling Pose and Object for image editing with Soft Attention Mask

引用

ACM Transactions on Multimedia Computing, Communications, and Applications 1000年

作者： Yue Zhang Chao Wang Feifei Fang Yunzhi Zhuge Hehe Fan Xiaojun Chang Cheng Deng Yi Yang Zhejiang University China University of Technology Sydney Australia Qingdao University of Technology China Dalian University of Technology China University of Science and Technology of China China Xidian University China

To achieve content-consistent results in text-conditioned image editing, existing methods typically employ a reconstruction branch to capture the source image details via diffusion inversion and a generation branch to synthesize the target image based on the given textual prompt and the masked source image details. However, accurately segmenting source details is challenging with the current fixed-threshold mask strategy. Additionally, the inadequacies in the inversion process can lead to insufficient retention of source details. In this paper, we propose a method called SAMControl (Soft Attention Mask) to adaptively control the pose and object details for image editing. SAMControl dynamically learns flexible attention masks for different images at various diffusion steps. Furthermore, in the reconstruction branch, we utilize a direct inversion technique to ensure the fidelity of source details within SAM. Extensive qualitative and quantitative results demonstrate the effectiveness of the proposed method.

关键词： text-guided image editing Soft Attention Mask Diffusion image Synthesis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：