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

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

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 publicationIEEE Winter Conference on Applications of Computer Vision (WACV)
Pages3203-3211
Number of pages8
Publication statusPublished - Mar 2020
EventIEEE Winter Conference on Applications of Computer Vision - Snowmass Village, United States
Duration: 2 Mar 20204 Mar 2020

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision
Abbreviated titleWACV 2020
CountryUnited States
CitySnowmass Village
Period2/03/204/03/20

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

    Kampelmühler, M. D., & Pinz, A. (2020). Synthesizing human-like sketches from natural images using a conditional convolutional decoder. In IEEE Winter Conference on Applications of Computer Vision (WACV) (pp. 3203-3211)