Free-Form Image Inpainting With Gated Convolution
Jiahui Yu,Zhe Lin,Jimei Yang,Xiaohui Shen,Xin Lu,Thomas S. Huang +5 more
- 22 Oct 2019
- pp 4470-4479
TL;DR: Yu et al. as mentioned in this paper proposed a generative image inpainting system to complete images with free-form mask and guidance, which is based on gated convolutions learned from millions of images without additional labeling efforts.
read more
Abstract: We present a generative image inpainting system to complete images with free-form mask and guidance. The system is based on gated convolutions learned from millions of images without additional labelling efforts. The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers. Moreover, as free-form masks may appear anywhere in images with any shape, global and local GANs designed for a single rectangular mask are not applicable. Thus, we also present a patch-based GAN loss, named SN-PatchGAN, by applying spectral-normalized discriminator on dense image patches. SN-PatchGAN is simple in formulation, fast and stable in training. Results on automatic image inpainting and user-guided extension demonstrate that our system generates higher-quality and more flexible results than previous methods. Our system helps user quickly remove distracting objects, modify image layouts, clear watermarks and edit faces. Code, demo and models are available at: \url{https://github.com/JiahuiYu/generative_inpainting}.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Grammatically Recognizing Images with Tree Convolution
Guangrun Wang,Guangcong Wang,Keze Wang,Xiaodan Liang,Liang Lin +4 more
- 23 Aug 2020
TL;DR: A simple yet effective tree convolution (TreeConv) operation for deep neural networks that designs a generative image grammar, i.e., tree generation rule, to parse the hierarchy of internal feature maps by generating tree structures and implicitly learning the specific visual grammars for each object category.
10
AutoRemover: Automatic Object Removal for Autonomous Driving Videos
Rong Zhang,Wei Li,Peng Wang,Chenye Guan,Jin Fang,Yuhang Song,Jinhui Yu,Baoquan Chen,Weiwei Xu,Ruigang Yang +9 more
- 03 Apr 2020
TL;DR: A video inpainting algorithm AutoRemover, designed specifically for generating street-view videos without any moving objects, which outperforms other state-of-the-art object removal algorithms, reducing the RMSE by over 19%.
Expression-Aware Face Reconstruction Via A Dual-Stream Network
Xiaoyu Chai,Jun Chen,Chao Liang,Xu Dongshu,Chia-Wen Lin +4 more
- 06 Jul 2020
TL;DR: A novel dual-stream network to deal with expression variations by proposing novel Attribute Spatial Maps to record the spatial information of facial identity and expression attributes in the 2D image space separately, thus keeping the identity information and further improving the ability to cope with expression changes.
10
Detecting and Removing Text in the Wild
TL;DR: Zhang et al. as mentioned in this paper proposed a new loss function for blending two tasks in a new network structure that depicts wild text regions in a soft mask and selectively inpaints them into a sensible background.
Interactive Separation Network For Image Inpainting
Siyuan Li,Lu Lu,Zhiqiang Zhang,Cheng Xin,Kepeng Xu,Wenxin Yu,Gang He,Jinjia Zhou,Zhuo Yang +8 more
- 01 Oct 2020
TL;DR: A brand-new network called Interactive Separation Network is designed that progressively decomposites the features into two streams and fuses them and the experimental results of proposed method are superior to state-of-the-art inpainting approaches.
10
References
U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger,Philipp Fischer,Thomas Brox +2 more
- 05 Oct 2015
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Squeeze-and-Excitation Networks
Jie Hu,Li Shen,Samuel Albanie,Gang Sun,Enhua Wu +4 more
- 18 Jun 2018
TL;DR: This work proposes a novel architectural unit, which is term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels and finds that SE blocks produce significant performance improvements for existing state-of-the-art deep architectures at minimal additional computational cost.
Image-to-Image Translation with Conditional Adversarial Networks
Phillip Isola,Jun-Yan Zhu,Tinghui Zhou,Alexei A. Efros +3 more
- 21 Jul 2017
TL;DR: Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Justin Johnson,Alexandre Alahi,Li Fei-Fei +2 more
- 08 Oct 2016
TL;DR: In this paper, the authors combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image style transfer, where a feedforward network is trained to solve the optimization problem proposed by Gatys et al. in real-time.