Related papers: Unsupervised Latent Space Translation Network
The Generator of a Generative Adversarial Network (GAN) is trained to transform latent vectors drawn from a prior distribution into realistic looking photos. These latent vectors have been shown to encode information about the content of…
In this paper, we have developed a general-purpose architecture, Vit-Gan, capable of performing most of the image-to-image translation tasks from semantic image segmentation to single image depth perception. This paper is a follow-up paper,…
We introduce a new architecture called a conditional invertible neural network (cINN), and use it to address the task of diverse image-to-image translation for natural images. This is not easily possible with existing INN models due to some…
Image translation across different domains has attracted much attention in both machine learning and computer vision communities. Taking the translation from source domain $\mathcal{D}_s$ to target domain $\mathcal{D}_t$ as an example,…
Place recognition is an essential component of Simultaneous Localization And Mapping (SLAM). Under severe appearance change, reliable place recognition is a difficult perception task since the same place is perceptually very different in…
Recent work has shown that a variety of semantics emerge in the latent space of Generative Adversarial Networks (GANs) when being trained to synthesize images. However, it is difficult to use these learned semantics for real image editing.…
Aiming towards human-level generalization, there is a need to explore adaptable representation learning methods with greater transferability. Most existing approaches independently address task-transferability and cross-domain adaptation,…
Deep image translation methods have recently shown excellent results, outputting high-quality images covering multiple modes of the data distribution. There has also been increased interest in disentangling the internal representations…
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results with only large monolingual corpora in each language. However, the uncertainty of associating target with source sentences makes UNMT theoretically an…
Unsupervised style transfer that supports diverse input styles using only one trained generator is a challenging and interesting task in computer vision. This paper proposes a Multi-IlluStrator Style Generative Adversarial Network (MISS…
Generative adversarial networks are the state of the art approach towards learned synthetic image generation. Although early successes were mostly unsupervised, bit by bit, this trend has been superseded by approaches based on labelled…
Learning a common representation space between vision and language allows deep networks to relate objects in the image to the corresponding semantic meaning. We present a model that learns a shared Gaussian mixture representation imposing…
Unpaired image-to-image translation has broad applications in art, design, and scientific simulations. One early breakthrough was CycleGAN that emphasizes one-to-one mappings between two unpaired image domains via generative-adversarial…
In many unpaired image domain translation problems, e.g., style transfer or super-resolution, it is important to keep the translated image similar to its respective input image. We propose the extremal transport (ET) which is a mathematical…
In this paper, we introduce Latent Bridge Matching (LBM), a new, versatile and scalable method that relies on Bridge Matching in a latent space to achieve fast image-to-image translation. We show that the method can reach state-of-the-art…
The Transformer architecture has achieved significant success in natural language processing, motivating its adaptation to computer vision tasks. Unlike convolutional neural networks, vision transformers inherently capture long-range…
Unsupervised image-to-image translation is an inherently ill-posed problem. Recent methods based on deep encoder-decoder architectures have shown impressive results, but we show that they only succeed due to a strong locality bias, and they…
Mixup augmentation has been widely integrated to generate adversarial examples with superior adversarial transferability when immigrating from a surrogate model to other models. However, the underlying mechanism influencing the mixup's…
Current image-to-image translation methods formulate the task with conditional generation models, leading to learning only the recolorization or regional changes as being constrained by the rich structural information provided by the…
In this paper, we explore illustrations in children's books as a new domain in unpaired image-to-image translation. We show that although the current state-of-the-art image-to-image translation models successfully transfer either the style…