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

Moritz Daniel Kampelmühler*, Axel Pinz

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paper

Abstract

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.
Original languageEnglish
Title of host publicationProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
Pages3192-3200
Number of pages9
ISBN (Electronic)9781728165530
DOIs
Publication statusPublished - Mar 2020
Eventwacv2020: WACV 2020 - Snowmass Village, United States
Duration: 1 Mar 20205 Mar 2020

Publication series

NameProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

Conference

Conferencewacv2020
Abbreviated titleWACV 2020
CountryUnited States
CitySnowmass Village
Period1/03/205/03/20

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Synthesizing human-like sketches from natural images using a conditional convolutional decoder'. Together they form a unique fingerprint.

Cite this