中文
相关论文

相关论文: Text Embedding is Not All You Need: Attention Cont…

200 篇论文

Text-to-image generation has recently seen remarkable success, granting users with the ability to create high-quality images through the use of text. However, contemporary methods face challenges in capturing the precise semantics conveyed…

计算机视觉与模式识别 · 计算机科学 2025-12-16 Shay Shomer-Chai , Wenxuan Peng , Bharath Hariharan , Hadar Averbuch-Elor

Image inpainting task requires filling the corrupted image with contents coherent with the context. This research field has achieved promising progress by using neural image inpainting methods. Nevertheless, there is still a critical…

计算机视觉与模式识别 · 计算机科学 2021-03-23 Lisai Zhang , Qingcai Chen , Baotian Hu , Shuoran Jiang

Subject-driven text-to-image diffusion models empower users to tailor the model to new concepts absent in the pre-training dataset using a few sample images. However, prevalent subject-driven models primarily rely on single-concept input…

计算机视觉与模式识别 · 计算机科学 2024-02-16 Junjie Shentu , Matthew Watson , Noura Al Moubayed

Multi-label image classification is a prediction task that aims to identify more than one label from a given image. This paper considers the semantic consistency of the latent space between the visual patch and linguistic label domains and…

计算机视觉与模式识别 · 计算机科学 2023-08-21 Miaoge Li , Dongsheng Wang , Xinyang Liu , Zequn Zeng , Ruiying Lu , Bo Chen , Mingyuan Zhou

Text-to-image diffusion models have advanced towards more controllable generation via supporting various additional conditions (e.g.,depth map, bounding box) beyond text. However, these models are learned based on the premise of perfect…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Luozhou Wang , Guibao Shen , Wenhang Ge , Guangyong Chen , Yijun Li , Ying-cong Chen

Recent advances in text-to-image models have enabled high-quality personalized image synthesis of user-provided concepts with flexible textual control. In this work, we analyze the limitations of two primary techniques in text-to-image…

计算机视觉与模式识别 · 计算机科学 2024-06-10 Lianyu Pang , Jian Yin , Baoquan Zhao , Feize Wu , Fu Lee Wang , Qing Li , Xudong Mao

Recent advances in image editing have shifted from manual pixel manipulation to employing deep learning methods like stable diffusion models, which now leverage cross-attention mechanisms for text-driven control. This transition has…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Linn Bieske , Carla Lorente

Recent advances in generative video models have enabled the creation of high-quality videos based on natural language prompts. However, these models frequently lack fine-grained temporal control, meaning they do not allow users to specify…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Shira Schiber , Ofir Lindenbaum , Idan Schwartz

Current diffusion models create photorealistic images given a text prompt as input but struggle to correctly bind attributes mentioned in the text to the right objects in the image. This is evidenced by our novel image-graph alignment model…

计算机视觉与模式识别 · 计算机科学 2024-04-23 Maria Mihaela Trusca , Wolf Nuyts , Jonathan Thomm , Robert Honig , Thomas Hofmann , Tinne Tuytelaars , Marie-Francine Moens

Recent advances in text-to-image diffusion models have enabled the photorealistic generation of images from text prompts. Despite the great progress, existing models still struggle to generate compositional multi-concept images naturally,…

计算机视觉与模式识别 · 计算机科学 2023-10-12 Hazarapet Tunanyan , Dejia Xu , Shant Navasardyan , Zhangyang Wang , Humphrey Shi

Text-to-image diffusion models particularly Stable Diffusion, have revolutionized the field of computer vision. However, the synthesis quality often deteriorates when asked to generate images that faithfully represent complex prompts…

计算机视觉与模式识别 · 计算机科学 2024-10-01 Chenyi Zhuang , Ying Hu , Pan Gao

Image translation between two domains is a class of problems aiming to learn mapping from an input image in the source domain to an output image in the target domain. It has been applied to numerous domains, such as data augmentation,…

计算机视觉与模式识别 · 计算机科学 2019-06-06 Chao Yang , Taehwan Kim , Ruizhe Wang , Hao Peng , C. -C. Jay Kuo

Semantic correspondence is the problem of establishing correspondences across images depicting different instances of the same object or scene class. One of recent approaches to this problem is to estimate parameters of a global…

计算机视觉与模式识别 · 计算机科学 2018-10-29 Paul Hongsuck Seo , Jongmin Lee , Deunsol Jung , Bohyung Han , Minsu Cho

Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object…

计算机视觉与模式识别 · 计算机科学 2024-02-01 Zhipeng Bao , Yijun Li , Krishna Kumar Singh , Yu-Xiong Wang , Martial Hebert

Recent advancements in text-to-image synthesis have been largely propelled by diffusion-based models, yet achieving precise alignment between text prompts and generated images remains a persistent challenge. We find that this difficulty…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Xiefan Guo , Xinzhu Ma , Haiyu Zhang , Di Huang

Representing the cutting-edge technique of text-to-image models, the latest Multimodal Diffusion Transformer (MMDiT) largely mitigates many generation issues existing in previous models. However, we discover that it still suffers from…

计算机视觉与模式识别 · 计算机科学 2024-11-28 Tianyi Wei , Dongdong Chen , Yifan Zhou , Xingang Pan

Self-supervised methods have shown remarkable progress in learning high-level semantics and low-level temporal correspondence. Building on these results, we take one step further and explore the possibility of integrating these two features…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Rui Qian , Shuangrui Ding , Xian Liu , Dahua Lin

Text alignment finds application in tasks such as citation recommendation and plagiarism detection. Existing alignment methods operate at a single, predefined level and cannot learn to align texts at, for example, sentence and document…

计算与语言 · 计算机科学 2020-10-06 Xuhui Zhou , Nikolaos Pappas , Noah A. Smith

Deep Text-to-Image Synthesis (TIS) models such as Stable Diffusion have recently gained significant popularity for creative Text-to-image generation. Yet, for domain-specific scenarios, tuning-free Text-guided Image Editing (TIE) is of…

计算机视觉与模式识别 · 计算机科学 2024-03-07 Bingyan Liu , Chengyu Wang , Tingfeng Cao , Kui Jia , Jun Huang

Recent advancements in text-to-image generative models have demonstrated a remarkable ability to capture a deep semantic understanding of images. In this work, we leverage this semantic knowledge to transfer the visual appearance between…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Yuval Alaluf , Daniel Garibi , Or Patashnik , Hadar Averbuch-Elor , Daniel Cohen-Or