中文
相关论文

相关论文: Inversion-by-Inversion: Exemplar-based Sketch-to-P…

200 篇论文

Geometry- and appearance-controlled full-body human image generation is an interesting but challenging task. Existing solutions are either unconditional or dependent on coarse conditions (e.g., pose, text), thus lacking explicit geometry…

计算机视觉与模式识别 · 计算机科学 2024-04-25 Linzi Qu , Jiaxiang Shang , Hui Ye , Xiaoguang Han , Hongbo Fu

Sketch-based image manipulation is an interactive image editing task to modify an image based on input sketches from users. Existing methods typically formulate this task as a conditional inpainting problem, which requires users to draw an…

计算机视觉与模式识别 · 计算机科学 2021-12-01 Yu Zeng , Zhe Lin , Vishal M. Patel

Generative models transform random noise into images; their inversion aims to transform images back to structured noise for recovery and editing. This paper addresses two key tasks: (i) inversion and (ii) editing of a real image using…

机器学习 · 计算机科学 2024-10-15 Litu Rout , Yujia Chen , Nataniel Ruiz , Constantine Caramanis , Sanjay Shakkottai , Wen-Sheng Chu

We propose CatVersion, an inversion-based method that learns the personalized concept through a handful of examples. Subsequently, users can utilize text prompts to generate images that embody the personalized concept, thereby achieving…

计算机视觉与模式识别 · 计算机科学 2023-12-01 Ruoyu Zhao , Mingrui Zhu , Shiyin Dong , Nannan Wang , Xinbo Gao

Synthesizing face images from monochrome sketches is one of the most fundamental tasks in the field of image-to-image translation. However, it is still challenging to (1)~make models learn the high-dimensional face features such as geometry…

计算机视觉与模式识别 · 计算机科学 2023-02-28 Yichen Peng , Chunqi Zhao , Haoran Xie , Tsukasa Fukusato , Kazunori Miyata

Diffusion models have dramatically advanced text-to-image generation in recent years, translating abstract concepts into high-fidelity images with remarkable ease. In this work, we examine whether they can also blend distinct concepts,…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Lorenzo Olearo , Giorgio Longari , Alessandro Raganato , Rafael Peñaloza , Simone Melzi

A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.They either finetune the model, or invert the image in the latent space of the pretrained model. However,…

计算机视觉与模式识别 · 计算机科学 2024-12-09 Senmao Li , Joost van de Weijer , Taihang Hu , Fahad Shahbaz Khan , Qibin Hou , Yaxing Wang , Jian Yang , Ming-Ming Cheng

Text-guided non-rigid editing involves complex edits for input images, such as changing motion or compositions within their surroundings. Since it requires manipulating the input structure, existing methods often struggle with preserving…

计算机视觉与模式识别 · 计算机科学 2024-10-17 Yunji Jung , Seokju Lee , Tair Djanibekov , Hyunjung Shim , Jong Chul Ye

Text-conditional image editing is a practical AIGC task that has recently emerged with great commercial and academic value. For real image editing, most diffusion model-based methods use DDIM Inversion as the first stage before editing.…

计算机视觉与模式识别 · 计算机科学 2024-12-17 Jiancheng Huang , Yi Huang , Jianzhuang Liu , Donghao Zhou , Yifan Liu , Shifeng Chen

Text-to-image diffusion generative models can generate high quality images at the cost of tedious prompt engineering. Controllability can be improved by introducing layout conditioning, however existing methods lack layout editing ability…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Alessandro Fontanella , Petru-Daniel Tudosiu , Yongxin Yang , Shifeng Zhang , Sarah Parisot

Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions. Yet, these models often struggle with interpreting spatial arrangements…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Jiaqi Liu , Tao Huang , Chang Xu

Recent advances in diffusion models have significantly improved text-to-image (T2I) generation, but they often struggle to balance fine-grained precision with high-level control. Methods like ControlNet and T2I-Adapter excel at following…

计算机视觉与模式识别 · 计算机科学 2025-04-11 Pouyan Navard , Amin Karimi Monsefi , Mengxi Zhou , Wei-Lun Chao , Alper Yilmaz , Rajiv Ramnath

Recent text-to-image diffusion models have demonstrated an astonishing capacity to generate high-quality images. However, researchers mainly studied the way of synthesizing images with only text prompts. While some works have explored using…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Jinheng Xie , Yuexiang Li , Yawen Huang , Haozhe Liu , Wentian Zhang , Yefeng Zheng , Mike Zheng Shou

The Stable Diffusion model is a prominent text-to-image generation model that relies on a text prompt as its input, which is encoded using the Contrastive Language-Image Pre-Training (CLIP). However, text prompts have limitations when it…

计算机视觉与模式识别 · 计算机科学 2024-02-16 Yuxuan Ding , Chunna Tian , Haoxuan Ding , Lingqiao Liu

Diffusion models have emerged as the leading approach for image synthesis, demonstrating exceptional photorealism and diversity. However, training diffusion models at high resolutions remains computationally prohibitive, and existing…

计算机视觉与模式识别 · 计算机科学 2025-06-26 Tobias Vontobel , Seyedmorteza Sadat , Farnood Salehi , Romann M. Weber

Image inversion is a fundamental task in generative models, aiming to map images back to their latent representations to enable downstream applications such as editing, restoration, and style transfer. This paper provides a comprehensive…

计算机视觉与模式识别 · 计算机科学 2025-02-18 Yinan Chen , Jiangning Zhang , Yali Bi , Xiaobin Hu , Teng Hu , Zhucun Xue , Ran Yi , Yong Liu , Ying Tai

Guided image synthesis enables everyday users to create and edit photo-realistic images with minimum effort. The key challenge is balancing faithfulness to the user input (e.g., hand-drawn colored strokes) and realism of the synthesized…

计算机视觉与模式识别 · 计算机科学 2022-01-06 Chenlin Meng , Yutong He , Yang Song , Jiaming Song , Jiajun Wu , Jun-Yan Zhu , Stefano Ermon

In image editing employing diffusion models, it is crucial to preserve the reconstruction fidelity to the original image while changing its style. Although existing methods ensure reconstruction fidelity through optimization, a drawback of…

计算机视觉与模式识别 · 计算机科学 2024-12-11 Daiki Miyake , Akihiro Iohara , Yu Saito , Toshiyuki Tanaka

Diffusion models have achieved remarkable success in the domain of text-guided image generation and, more recently, in text-guided image editing. A commonly adopted strategy for editing real images involves inverting the diffusion process…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Wonjun Kang , Kevin Galim , Hyung Il Koo

Recently, text-to-3D approaches have achieved high-fidelity 3D content generation using text description. However, the generated objects are stochastic and lack fine-grained control. Sketches provide a cheap approach to introduce such…

计算机视觉与模式识别 · 计算机科学 2024-01-30 Minglin Chen , Weihao Yuan , Yukun Wang , Zhe Sheng , Yisheng He , Zilong Dong , Liefeng Bo , Yulan Guo