arXiv research

CAFLOW uses auto-regressive flows to translate images efficiently.

The Hilbert map's image is discussed, showing when it's surjective.

Framework generates realistic crop images for growth modeling.

The recent success of Generative Adversarial Networks (GAN) is a result of their ability to generate high quality images from a latent vector space. An important application is the generation of images from a text description, where the text description is encoded and further used in the conditioning of the generated i…

We are interested in attribute-guided face generation: given a low-res face input image, an attribute vector that can be extracted from a high-res image (attribute image), our new method generates a high-res face image for the low-res input that satisfies the given attributes. To address this problem, we condition the …

HW2MP-GAN tackles ancient handwritten text recognition.

LcGAN generates synthetic CT images for hemorrhagic lesion segmentation.

DiffDenoise preserves fine structures in medical images using conditional diffusion models.

A method to improve image synthesis diversity using mutual information.

Recent advances in conditional image generation tasks, such as image-to-image translation and image inpainting, are largely accounted to the success of conditional GAN models, which are often optimized by the joint use of the GAN loss with the reconstruction loss. However, we reveal that this training recipe shared by …

Plug-and-play multimodal controller improves class-conditional image generation.

This work introduces an efficient method to sample high-quality images from conditional GANs.

Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing text-to-image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In…

Unified method for multi-defect microscopy image restoration with limited training data.

Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We construct a variant of GANs employing label conditioning that results in 128x128 r…

Image captioning has demonstrated models that are capable of generating plausible text given input images or videos. Further, recent work in image generation has shown significant improvements in image quality when text is used as a prior. Our work ties these concepts together by creating an architecture that can enabl…

Generative model extracts road networks from images.

Generative model generates images with multiple object classes.

I$^2$SB learns nonlinear diffusion processes between images.

This work proves intrinsic robustness bounds for natural image distributions.

SNS-GAN integrates class labels into generative models for images and time series.

A new model improves medical image segmentation uncertainty.

Polarimetric images enhance object detection in adverse weather conditions.

YuruGAN generates yuru-chara images using GANs and clustering for small datasets.

Conditional domain generation is a good way to interactively control sample generation process of deep generative models. However, once a conditional generative model has been created, it is often expensive to allow it to adapt to new conditional controls, especially the network structure is relatively deep. We propose…

A new method learns continuous guidance weights to improve diffusion model quality and distributional alignment.

Paper proposes method to generate images from text using GANs trained on uncaptioned images.

Generative model creates realistic scenes from pixel-wise labels.

We present a conditional generative model to learn variation in cell and nuclear morphology and the location of subcellular structures from microscopy images. Our model generalizes to a wide range of subcellular localization and allows for a probabilistic interpretation of cell and nuclear morphology and structure loca…

CSI method learns conditional distributions by estimating flow equations.

We introduce MosAIc, an interactive web app that allows users to find pairs of semantically related artworks that span different cultures, media, and millennia. To create this application, we introduce Conditional Image Retrieval (CIR) which combines visual similarity search with user supplied filters or "conditions". …

We propose Progressive Structure-conditional Generative Adversarial Networks (PSGAN), a new framework that can generate full-body and high-resolution character images based on structural information. Recent progress in generative adversarial networks with progressive training has made it possible to generate high-resol…

New method for generating images with conditional probability models.

We propose a novel, projection based way to incorporate the conditional information into the discriminator of GANs that respects the role of the conditional information in the underlining probabilistic model. This approach is in contrast with most frameworks of conditional GANs used in application today, which use the …

Conventional SVM-based image coding methods are founded on independently restricting the distortion in every image coefficient at some particular image representation. Geometrically, this implies allowing arbitrary signal distortions in an $n$-dimensional rectangle defined by the $\varepsilon$-insensitivity zone in eac…

Recent sparse MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning. However, these techniques sometimes struggle to reconstruct sharp images that preserve fine detail while maintaining a nat…

Unsupervised image-to-image translation is an important and challenging problem in computer vision. Given an image in the source domain, the goal is to learn the conditional distribution of corresponding images in the target domain, without seeing any pairs of corresponding images. While this conditional distribution i…

In this article we give our contribution to the problem of segmentation with plug-in procedures. We give general sufficient conditions under which plug in procedure are efficient. We also give an algorithm that satisfy these conditions. We give an application of the used algorithm to hyperspectral images segmentation. …

Unsupervised image inpainting models generate plausible reconstructions from incomplete data.

AR-CSM models use derivatives of univariate log-conditionals to estimate joint distributions efficiently.

Learning the distribution of natural images is one of the hardest and most important problems in machine learning. The problem remains open, because the enormous complexity of the structures in natural images spans all length scales. We break down the complexity of the problem and show that the hierarchy of structures …

When training a deep neural network for image classification, one can broadly distinguish between two types of latent features of images that will drive the classification. We can divide latent features into (i) "core" or "conditionally invariant" features $X^\text{core}$ whose distribution $X^\text{core}\vert Y$, cond…

This paper studies the problem of learning the conditional distribution of a high-dimensional output given an input, where the output and input may belong to two different domains, e.g., the output is a photo image and the input is a sketch image. We solve this problem by cooperative training of a fast thinking initial…

In this work we propose a new computational framework, based on generative deep models, for synthesis of photo-realistic food meal images from textual descriptions of its ingredients. Previous works on synthesis of images from text typically rely on pre-trained text models to extract text features, followed by a genera…

CcGAN tackles conditional image generation for continuous labels.

Study evaluates deep learning methods for dermatology, finding they perform poorly under non-ideal conditions.

Improved person detection in occluded conditions with AOS images.

Bayesian tensor network reduces conditional probability calculation to polynomial time.