Automatic Object Recoloring Using Adversarial Learning
Jan 26, 2021
Cycle Consistency Loss
3 videos · undefined sub area
Generative Adversarial Networks
539 videos · undefined sub area
Abstract: We propose a novel method for automatic object recoloring based on Generative Adversarial Networks (GANs). The user can simply give commands of the form ""recolor
"" which will be executed without any need of manual edit. Our approach takes advantage of pre-trained object detectors and saliency mask segmentation networks. The segmented mask of the given object along with the target color and the original image form the input to the GAN. The use of cycle consistency loss ensures the realistic look of the results. To our best knowledge, this is the first algorithm where the automatic recoloring is only limited by the ability of the mask extractor to map a natural language tag to a specific object in the image (several hundred object types at the time of this writing). For a performance comparison, we also adapted other state of the art methods to perform this task. We found that our method had consistently yielded qualitatively better recoloring results. Authors: Siavash Khodadadeh, Saeid Motiian, Zhe Lin, Ladislau Boloni, Shabnam Ghadar (University of Central Florida)
Category: WACV 2021
📝 No reactions yet
Be the first one to share your thoughts!
Playing Atari with Deep Reinforcement Learning | Two Minute Paper
Two Minute Papers
| Mar 7, 2015
ICAPS 2014: Menkes van den Briel on "Flow-based Heuristics for Optimal Planning"
| Mar 13, 2015
ICAPS 2014: Jendrik Seipp on "Diverse and Additive Cartesian Abstraction Heuristics"
| Apr 14, 2015
ICAPS 2014: Bram Ridder on "Heuristic Evaluation Based on Lifted Relaxed Planning Graphs"
| Apr 14, 2015
ICAPS 2014: Richard Valenzano on "A Comparison of Knowledge-Based GBFS Enhancements and..."
| Apr 15, 2015
Crossminds Chrome Extension
Watch videos on arXiv
Subscribe to Our Newsletter
AI Startup Jobs
Terms & Conditions
© Provided by CrossCircles Inc.