中文
相关论文

相关论文: Structure First Detail Next: Image Inpainting with…

200 篇论文

Reference-guided image inpainting restores image pixels by leveraging the content from another single reference image. The primary challenge is how to precisely place the pixels from the reference image into the hole region. Therefore,…

计算机视觉与模式识别 · 计算机科学 2022-10-11 Yunhan Zhao , Connelly Barnes , Yuqian Zhou , Eli Shechtman , Sohrab Amirghodsi , Charless Fowlkes

Recent GAN-based image inpainting approaches adopt an average strategy to discriminate the generated image and output a scalar, which inevitably lose the position information of visual artifacts. Moreover, the adversarial loss and…

计算机视觉与模式识别 · 计算机科学 2020-11-18 Ruisong Zhang , Weize Quan , Baoyuan Wu , Zhifeng Li , Dong-Ming Yan

Recovering the missing regions of an image is a task that is called image inpainting. Depending on the shape of missing areas, different methods are presented in the literature. One of the challenges of this problem is extracting features…

计算机视觉与模式识别 · 计算机科学 2020-01-13 Ghazale Ghorbanzade , Zahra Nabizadeh , Nader Karimi , Shadrokh Samavi

We propose a novel method of efficient upsampling of a single natural image. Current methods for image upsampling tend to produce high-resolution images with either blurry salient edges, or loss of fine textural detail, or spurious noise…

计算机视觉与模式识别 · 计算机科学 2015-03-03 Chinmay Hegde , Oncel Tuzel , Fatih Porikli

Deep-neural-network-based image reconstruction has demonstrated promising performance in medical imaging for under-sampled and low-dose scenarios. However, it requires large amount of memory and extensive time for the training. It is…

计算机视觉与模式识别 · 计算机科学 2019-06-12 Dufan Wu , Kyungsang Kim , Quanzheng Li

Distinguishing between computer-generated (CG) and natural photographic (PG) images is of great importance to verify the authenticity and originality of digital images. However, the recent cutting-edge generation methods enable high…

计算机视觉与模式识别 · 计算机科学 2022-09-08 Qiang Xu , Shan Jia , Xinghao Jiang , Tanfeng Sun , Zhe Wang , Hong Yan

We propose an approach to 3D reconstruction via inverse procedural modeling and investigate two variants of this approach. The first option consists in the fitting set of input parameters using a genetic algorithm. We demonstrate the…

图形学 · 计算机科学 2023-10-23 Albert Garifullin , Nikolay Maiorov , Vladimir Frolov

In the recent years, there has been a significant improvement in the quality of samples produced by (deep) generative models such as variational auto-encoders and generative adversarial networks. However, the representation capabilities of…

图像与视频处理 · 电气工程与系统科学 2026-03-31 Shady Abu Hussein , Tom Tirer , Raja Giryes

We present a new data-driven video inpainting method for recovering missing regions of video frames. A novel deep learning architecture is proposed which contains two sub-networks: a temporal structure inference network and a spatial detail…

计算机视觉与模式识别 · 计算机科学 2018-12-04 Chuan Wang , Haibin Huang , Xiaoguang Han , Jue Wang

We present a generative method for texture filtering, which exhibits surprisingly good performance and generalizability. Our core idea is to empower texture filtering by taking full advantage of the strong learned image prior of pre-trained…

计算机视觉与模式识别 · 计算机科学 2026-04-22 Rongjia Zheng , Shangwei Huang , Lei Zhu , Wei-Shi Zheng , Qing Zhang

Image Inpainting is one of the very popular tasks in the field of image processing with broad applications in computer vision. In various practical applications, images are often deteriorated by noise due to the presence of corrupted, lost,…

计算机视觉与模式识别 · 计算机科学 2021-08-20 Harsh Patel , Amey Kulkarni , Shivam Sahni , Udit Vyas

Image denoising is a fundamental and challenging task in the field of computer vision. Most supervised denoising methods learn to reconstruct clean images from noisy inputs, which have intrinsic spectral bias and tend to produce…

计算机视觉与模式识别 · 计算机科学 2023-09-20 Yujin Wang , Lingen Li , Tianfan Xue , Jinwei Gu

This paper proposes a novel framework to regularize the highly ill-posed and non-linear Fourier ptychography problem using generative models. We demonstrate experimentally that our proposed algorithm, Deep Ptych, outperforms the existing…

机器学习 · 计算机科学 2018-12-31 Fahad Shamshad , Farwa Abbas , Ali Ahmed

Despite the success of Generative Adversarial Networks (GANs) in image synthesis, applying trained GAN models to real image processing remains challenging. Previous methods typically invert a target image back to the latent space either by…

计算机视觉与模式识别 · 计算机科学 2020-04-01 Jinjin Gu , Yujun Shen , Bolei Zhou

Most existing methods for image inpainting focus on learning the intra-image priors from the known regions of the current input image to infer the content of the corrupted regions in the same image. While such methods perform well on images…

计算机视觉与模式识别 · 计算机科学 2022-03-22 Xin Feng , Wenjie Pei , Fengjun Li , Fanglin Chen , David Zhang , Guangming Lu

Image outpainting seeks for a semantically consistent extension of the input image beyond its available content. Compared to inpainting -- filling in missing pixels in a way coherent with the neighboring pixels -- outpainting can be…

计算机视觉与模式识别 · 计算机科学 2021-04-02 Yen-Chi Cheng , Chieh Hubert Lin , Hsin-Ying Lee , Jian Ren , Sergey Tulyakov , Ming-Hsuan Yang

Image inpainting is the task of plausibly restoring missing pixels within a hole region that is to be removed from a target image. Most existing technologies exploit patch similarities within the image, or leverage large-scale training data…

计算机视觉与模式识别 · 计算机科学 2021-03-31 Yuqian Zhou , Connelly Barnes , Eli Shechtman , Sohrab Amirghodsi

Learning a dense 3D model with fine-scale details from a single facial image is highly challenging and ill-posed. To address this problem, many approaches fit smooth geometries through facial prior while learning details as additional…

计算机视觉与模式识别 · 计算机科学 2022-03-21 Xingyu Ren , Alexandros Lattas , Baris Gecer , Jiankang Deng , Chao Ma , Xiaokang Yang , Stefanos Zafeiriou

Recent works in image inpainting have shown that structural information plays an important role in recovering visually pleasing results. In this paper, we propose an end-to-end architecture composed of two parallel UNet-based streams: a…

计算机视觉与模式识别 · 计算机科学 2021-11-08 Zhilin Huang , Chujun Qin , Ruixin Liu , Zhenyu Weng , Yuesheng Zhu

Image inpainting seeks a semantically consistent way to recover the corrupted image in the light of its unmasked content. Previous approaches usually reuse the well-trained GAN as effective prior to generate realistic patches for missing…

计算机视觉与模式识别 · 计算机科学 2022-08-26 Yongsheng Yu , Libo Zhang , Heng Fan , Tiejian Luo