Synthesizing human-like sketches from natural images using a conditional convolutional decoder

03/16/2020
by   Moritz Kampelmühler, et al.
15

Humans are able to precisely communicate diverse concepts by employing sketches, a highly reduced and abstract shape based representation of visual content. We propose, for the first time, a fully convolutional end-to-end architecture that is able to synthesize human-like sketches of objects in natural images with potentially cluttered background. To enable an architecture to learn this highly abstract mapping, we employ the following key components: (1) a fully convolutional encoder-decoder structure, (2) a perceptual similarity loss function operating in an abstract feature space and (3) conditioning of the decoder on the label of the object that shall be sketched. Given the combination of these architectural concepts, we can train our structure in an end-to-end supervised fashion on a collection of sketch-image pairs. The generated sketches of our architecture can be classified with 85.6 Top-5 accuracy and we verify their visual quality via a user study. We find that deep features as a perceptual similarity metric enable image translation with large domain gaps and our findings further show that convolutional neural networks trained on image classification tasks implicitly learn to encode shape information. Code is available under https://github.com/kampelmuehler/synthesizing_human_like_sketches

READ FULL TEXT

page 1

page 3

page 6

page 7

research
11/20/2017

End-to-end Trained CNN Encode-Decoder Networks for Image Steganography

All the existing image steganography methods use manually crafted featur...
research
02/17/2022

A study of deep perceptual metrics for image quality assessment

Several metrics exist to quantify the similarity between images, but the...
research
10/22/2018

Learning to Measure Change: Fully Convolutional Siamese Metric Networks for Scene Change Detection

The key factor of scene change detection is to learn effective feature t...
research
01/07/2018

Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature Encoding

A common approach for moving objects segmentation in a scene is to perfo...
research
03/07/2022

Explaining Classifiers by Constructing Familiar Concepts

Interpreting a large number of neurons in deep learning is difficult. Ou...
research
05/18/2021

Assessing aesthetics of generated abstract images using correlation structure

Can we generate abstract aesthetic images without bias from natural or h...
research
07/26/2018

Unified Perceptual Parsing for Scene Understanding

Humans recognize the visual world at multiple levels: we effortlessly ca...

Please sign up or login with your details

Forgot password? Click here to reset