Image Resizing by Reconstruction from Deep Features
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 imp...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. |
---|---|
DOI: | 10.48550/arxiv.1904.08475 |