Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation

Autor: Marco De Nadai, Yajing Chen, Bruno Lepri, Wei Wang, Linchao Bao, Nicu Sebe, Enver Sangineto, Haoxian Zhang, Yahui Liu
Jazyk: angličtina
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Computer Science - Machine Learning
Computer science
Computer Vision and Pattern Recognition (cs.CV)
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Computer Science - Computer Vision and Pattern Recognition
02 engineering and technology
Translation (geometry)
Semantics
Measure (mathematics)
Smoothing methods
Machine Learning (cs.LG)
030218 nuclear medicine & medical imaging
Image (mathematics)
03 medical and health sciences
0302 clinical medicine
0202 electrical engineering
electronic engineering
information engineering
Training
business.industry
Computational modeling
Pattern recognition
Interpolation
Metric (mathematics)
Image translation
Computer vision
020201 artificial intelligence & image processing
Artificial intelligence
business
Training
Interpolation
Computer vision
Smoothing methods
Protocols
Computational modeling
Semantics
Protocols
Smoothing
Zdroj: CVPR
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Popis: Image-to-Image (I2I) multi-domain translation models are usually evaluated also using the quality of their semantic interpolation results. However, state-of-the-art models frequently show abrupt changes in the image appearance during interpolation, and usually perform poorly in interpolations across domains. In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The content of the source image is better preserved during the translation. Moreover, we propose a novel evaluation metric to properly measure the smoothness of latent style space of I2I translation models. The proposed method can be plugged into existing translation approaches, and our extensive experiments on different datasets show that it can significantly boost the quality of the generated images and the graduality of the interpolations.
Accepted to CVPR 2021
Databáze: OpenAIRE
Externí odkaz: