中文
相关论文

相关论文: Light-weight pixel context encoders for image inpa…

200 篇论文

Recent deep learning based approaches have shown promising results for the challenging task of inpainting large missing regions in an image. These methods can generate visually plausible image structures and textures, but often create…

计算机视觉与模式识别 · 计算机科学 2018-03-23 Jiahui Yu , Zhe Lin , Jimei Yang , Xiaohui Shen , Xin Lu , Thomas S. Huang

Image restoration tasks traditionally rely on convolutional neural networks. However, given the local nature of the convolutional operator, they struggle to capture global information. The promise of attention mechanisms in Transformers is…

图像与视频处理 · 电气工程与系统科学 2024-05-08 Amirhosein Ghasemabadi , Muhammad Kamran Janjua , Mohammad Salameh , Chunhua Zhou , Fengyu Sun , Di Niu

Controllable text generation has taken a gigantic step forward these days. Yet existing methods are either constrained in a one-off pattern or not efficient enough for receiving multiple conditions at every generation stage. We propose a…

计算与语言 · 计算机科学 2022-10-10 Haoqin Tu , Zhongliang Yang , Jinshuai Yang , Siyu Zhang , Yongfeng Huang

Image inpainting technology can patch images with missing pixels. Existing methods propose convolutional neural networks to repair corrupted images. The networks focus on the valid pixels around the missing pixels, use the encoder-decoder…

计算机视觉与模式识别 · 计算机科学 2020-02-06 Zhenghang Wu , Yidong Cui

Variational Convertor-Encoder (VCE) converts an image to various styles; we present this novel architecture for the problem of one-shot generalization and its transfer to new tasks not seen before without additional training. We also…

计算机视觉与模式识别 · 计算机科学 2020-11-13 Chengshuai Li , Shuai Han , Jianping Xing

Different from image inpainting, image outpainting has relative less context in the image center to capture and more content at the image border to predict. Therefore, classical encoder-decoder pipeline of existing methods may not predict…

计算机视觉与模式识别 · 计算机科学 2020-10-28 Xiaofeng Zhang , Feng Chen , Cailing Wang , Songsong Wu , Ming Tao , Guoping Jiang

Deep neural networks have been successfully applied to problems such as image segmentation, image super-resolution, coloration and image inpainting. In this work we propose the use of convolutional neural networks (CNN) for image inpainting…

计算机视觉与模式识别 · 计算机科学 2018-02-13 Pascal Laube , Michael Grunwald , Matthias O. Franz , Georg Umlauf

Partial Differential Equations (PDEs) have long been recognized as powerful tools for image processing and analysis, providing a framework to model and exploit structural and geometric properties inherent in visual data. Over the years,…

图像与视频处理 · 电气工程与系统科学 2024-12-17 Alejandro Garnung Menéndez

Context-dependence in human cognition process is a well-established fact. Following this, we introduced the image segmentation method that can use context to classify a pixel on the basis of its membership to a particular object-class of…

计算机视觉与模式识别 · 计算机科学 2012-02-10 Upendra Kumar , Tapobrata Lahiri , Manoj Kumar Pal

Image-to-image translation is a fundamental task in computer vision. It transforms images from one domain to images in another domain so that they have particular domain-specific characteristics. Most prior works train a generative model to…

计算机视觉与模式识别 · 计算机科学 2023-02-24 Sihan Xu , Zelong Jiang , Ruisi Liu , Kaikai Yang , Zhijie Huang

Inpainting-based codecs store sparse selected pixel data and decode by reconstructing the discarded image parts by inpainting. Successful codecs (coders and decoders) traditionally use inpainting operators that solve partial differential…

图像与视频处理 · 电气工程与系统科学 2024-06-21 Rahul Mohideen Kaja Mohideen , Tobias Alt , Pascal Peter , Joachim Weickert

Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approximation to constrain…

计算机视觉与模式识别 · 计算机科学 2019-04-02 Mu Li , Wangmeng Zuo , Shuhang Gu , Jane You , David Zhang

Existing video Variational Autoencoders (VAEs) generally overlook the similarity between frame contents, leading to redundant latent modeling. In this paper, we propose decoupled VAE (DeCo-VAE) to achieve compact latent representation.…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Xiangchen Yin , Jiahui Yuan , Zhangchi Hu , Wenzhang Sun , Jie Chen , Xiaozhen Qiao , Hao Li , Xiaoyan Sun

Recent advances in deep generative models have shown promising potential in image inpanting, which refers to the task of predicting missing pixel values of an incomplete image using the known context. However, existing methods can be slow…

计算机视觉与模式识别 · 计算机科学 2018-03-29 Chao Yang , Yuhang Song , Xiaofeng Liu , Qingming Tang , C. -C. Jay Kuo

Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional…

计算机视觉与模式识别 · 计算机科学 2017-07-11 Albert Jimenez , Jose M. Alvarez , Xavier Giro-i-Nieto

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based auto encoders have shown great potential in detecting anomalies in medical images. However, state-of-the-art…

机器学习 · 计算机科学 2018-12-17 David Zimmerer , Simon A. A. Kohl , Jens Petersen , Fabian Isensee , Klaus H. Maier-Hein

Remarkable progress in text-to-image diffusion models has brought a major concern about potentially generating images on inappropriate or trademarked concepts. Concept erasing has been investigated with the goals of deleting target concepts…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Byung Hyun Lee , Sungjin Lim , Seunggyu Lee , Dong Un Kang , Se Young Chun

Most deep learning based image inpainting approaches adopt autoencoder or its variants to fill missing regions in images. Encoders are usually utilized to learn powerful representational spaces, which are important for dealing with…

计算机视觉与模式识别 · 计算机科学 2020-10-30 Xin Ma , Xiaoqiang Zhou , Huaibo Huang , Zhenhua Chai , Xiaolin Wei , Ran He

Images can be viewed as layered compositions, foreground objects over background, with potential occlusions. This layered representation enables independent editing of elements, offering greater flexibility for content creation. Despite the…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Jingxi Chen , Yixiao Zhang , Xiaoye Qian , Zongxia Li , Cornelia Fermuller , Caren Chen , Yiannis Aloimonos

In an unpaired setting, lacking sufficient content constraints for image-to-image translation (I2I) tasks, GAN-based approaches are usually prone to model collapse. Current solutions can be divided into two categories, reconstruction-based…

计算机视觉与模式识别 · 计算机科学 2024-01-09 Xiuding Cai , Yaoyao Zhu , Dong Miao , Linjie Fu , Yu Yao