Image Resizing by Reconstruction from Deep Features

  title={Image Resizing by Reconstruction from Deep Features},
  author={Moab Arar and Dov Danon and Daniel Cohen-Or and Ariel Shamir},
  journal={Comput. Vis. Media},
Traditional image resizing methods usually work in pixel space and use various saliency measures. [...] Key Method This novel approach leverages the hierarchical encoding of the network, and in particular, the high-level discriminative power of its deeper layers, that recognizes semantic objects and regions and allows maintaining their aspect ratio. Our use of reconstruction from deep features diminishes the artifacts introduced by image-space resizing operators. We evaluate our method on benchmarks, compare to…Expand
Semantic Pyramid for Image Generation
A novel GAN-based model that utilizes the space of deep features learned by a pre-trained classification model as a Semantic Generation Pyramid, a hierarchical framework which leverages the continuum of semantic information encapsulated in such deep features. Expand
Structure preservation in content-aware image retargeting using multi-operator
A new multi-operator scheme is proposed which has improved seam carving, through the proposed seam diversion based image retargeting algorithm, integrated with the cropping and warping operator, which preserves the salient features of the retargeted images. Expand
Structure preservation of image using an efficient content-aware image retargeting technique
A novel and effective technique that vanquishes the problems encountered in the conventional seam carving method is proposed that shows remarkable results in terms of low distortion percentage. Expand
Roundness-Preserving Warping for Aesthetic Enhancement-Based Stereoscopic Image Editing
A roundness-preserving warping model for stereoscopic image editing, in which energy constraints from image quality energy, aesthetics energy and depth adaptation energy are involved in the framework to solve the optimization. Expand
An automated slice sorting technique for multi-slice computed tomography liver cancer images using convolutional network
  • Amandeep Kaur, Ajay Pal Singh Chauhan, Ashwani Kumar Aggarwal
  • Computer Science
  • 2021
Multi-organ classification of 3D CT images of liver cancer suspected patients by convolution network will help the radiation therapist to focus on a small subset of CT image data and will help in the rapid diagnosis and treatment of Liver cancer patients. Expand
Strategizing secured image storing and efficient image retrieval through a new cloud framework
This study proposes a strategy to enable faster and efficient image retrieval from a cloud via the necessary pre-processing of images beyond conventional online processing, and extends the abilities of cloud file sharing from the conventional “only storing images” to pre- processing along with security reinforcing. Expand


Image Style Transfer Using Convolutional Neural Networks
A Neural Algorithm of Artistic Style is introduced that can separate and recombine the image content and style of natural images and provide new insights into the deep image representations learned by Convolutional Neural Networks and demonstrate their potential for high level image synthesis and manipulation. Expand
Internal Distribution Matching for Natural Image Retargeting
A Deep-Learning approach for retargeting, based on an "Internal GAN" (InGAN), an image-specific GAN that incorporates the Internal statistics of a single natural image in a GAN and is able to synthesize natural looking target images composed from the input image patch-distribution. Expand
Photo Squarization by Deep Multi-Operator Retargeting
This study realizes photo squarization by modeling Retargeting Visual Perception Issues, which reflect human perception preference toward image ratargeting. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
Visual attribute transfer through deep image analogy
The technique finds semantically-meaningful dense correspondences between two input images by adapting the notion of "image analogy" with features extracted from a Deep Convolutional Neutral Network for matching, and is called deep image analogy. Expand
Seam carving for content-aware image resizing
Effective resizing of images should not only use geometric constraints, but consider the image content as well. We present a simple image operator called seam carving that supports content-awareExpand
Resizing by symmetry-summarization
Image resizing can be achieved more effectively if we have a better understanding of the image semantics. In this paper, we analyze the translational symmetry, which exists in many real-world images.Expand
SinGAN: Learning a Generative Model From a Single Natural Image
We introduce SinGAN, an unconditional generative model that can be learned from a single natural image. Our model is trained to capture the internal distribution of patches within the image, and isExpand
Optimized scale-and-stretch for image resizing
We present a "scale-and-stretch" warping method that allows resizing images into arbitrary aspect ratios while preserving visually prominent features. The method operates by iteratively computingExpand
Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting
This paper proposes a weakly- and self-supervised deep convolutional neural network (WSSDCNN) for contentaware image retargeting. Our network takes a source image and a target aspect ratio, and thenExpand