One-to-one Mapping for Unpaired Image-to-image Translation
arXiv:1909.04110
Abstract
Recently image-to-image translation has attracted significant interests in the literature, starting from the successful use of the generative adversarial network (GAN), to the introduction of cyclic constraint, to extensions to multiple domains. However, in existing approaches, there is no guarantee that the mapping between two image domains is unique or one-to-one. Here we propose a self-inverse network learning approach for unpaired image-to-image translation. Building on top of CycleGAN, we learn a self-inverse function by simply augmenting the training samples by swapping inputs and outputs during training and with separated cycle consistency loss for each mapping direction. The outcome of such learning is a proven one-to-one mapping function. Our extensive experiments on a variety of datasets, including cross-modal medical image synthesis, object transfiguration, and semantic labeling, consistently demonstrate clear improvement over the CycleGAN method both qualitatively and quantitatively. Especially our proposed method reaches the state-of-the-art result on the cityscapes benchmark dataset for the label to photo unpaired directional image translation.
arXiv commentAccepted by WACV 2020
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
- Unsupervised Attention-guided Image to Image Translation
- Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
- DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
- i-RevNet: Deep Invertible Networks
- Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
- Harmonic Unpaired Image-to-image Translation
- Smart, Sparse Contours to Represent and Edit Images
- Towards Learning a Self-inverse Network for Bidirectional Image-to-image Translation
- Guiding the One-to-one Mapping in CycleGAN via Optimal Transport