Image Resizing by Reconstruction from Deep Features

04/17/2019
by   Moab Arar, et al.
0

Traditional image resizing methods usually work in pixel space and use various saliency measures. The challenge is to adjust the image shape while trying to preserve important content. In this paper we perform image resizing in feature space where the deep layers of a neural network contain rich important semantic information. We directly adjust the image feature maps, extracted from a pre-trained classification network, and reconstruct the resized image using a neural-network based optimization. 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 alternative approaches, and demonstrate its strength on challenging images.

READ FULL TEXT

page 4

page 6

page 7

page 8

page 9

page 10

page 11

page 12

research
03/13/2020

Semantic Pyramid for Image Generation

We present a novel GAN-based model that utilizes the space of deep featu...
research
06/04/2019

Cross-Domain Cascaded Deep Feature Translation

In recent years we have witnessed tremendous progress in unpaired image-...
research
04/04/2018

A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI

Compressed sensing MRI is a classic inverse problem in the field of comp...
research
06/26/2018

Deep Feature Factorization For Concept Discovery

We propose Deep Feature Factorization (DFF), a method capable of localiz...
research
06/21/2021

Cross-layer Navigation Convolutional Neural Network for Fine-grained Visual Classification

Fine-grained visual classification (FGVC) aims to classify sub-classes o...
research
08/14/2019

Visualizing Image Content to Explain Novel Image Discovery

The initial analysis of any large data set can be divided into two phase...
research
07/10/2020

Impression Space from Deep Template Network

It is an innate ability for humans to imagine something only according t...

Please sign up or login with your details

Forgot password? Click here to reset