Browse > Computer Vision > Image Generation

Image Generation

117 papers with code · Computer Vision

Image generation (synthesis) is the task of generating new images from an existing dataset.

State-of-the-art leaderboards

Latest papers with code

Synthesizing New Retinal Symptom Images by Multiple Generative Models

11 Feb 2019huckiyang/EyeNet-GANs

Age-Related Macular Degeneration (AMD) is an asymptomatic retinal disease which may result in loss of vision. There is limited access to high-quality relevant retinal images and poor understanding of the features defining sub-classes of this disease.


11 Feb 2019

Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design

ICLR 2019 aravind0706/flowpp

Flow-based generative models are powerful exact likelihood models with efficient sampling and inference. Despite their computational efficiency, flow-based models generally have much worse density modeling performance compared to state-of-the-art autoregressive models.


01 Feb 2019

FaceForensics++: Learning to Detect Manipulated Facial Images

25 Jan 2019ondyari/FaceForensics

The rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns on the implication on the society. At best, this leads to a loss of trust in digital content, but it might even cause further harm by spreading false information and the creation of fake news.


Virtual Conditional Generative Adversarial Networks

25 Jan 2019annonnymmouss/vcgan

When trained on multimodal image datasets, normal Generative Adversarial Networks (GANs) are usually outperformed by class-conditional GANs and ensemble GANs, but conditional GANs is restricted to labeled datasets and ensemble GANs lack efficiency. All the generative paths share the same decoder network while in each path the decoder network is fed with a concatenation of a different pre-computed amplified one-hot vector and the inputted Gaussian noise.


25 Jan 2019

CSGAN: Cyclic-Synthesized Generative Adversarial Networks for Image-to-Image Transformation

11 Jan 2019KishanKancharagunta/CSGAN

Most of the research has been focused on the task of image transformation for a set of pre-defined domains. Most of the research focuses over the suitable objective function for image-to-image transformation.


11 Jan 2019

FIGR: Few-shot Image Generation with Reptile

8 Jan 2019marcdemers/FIGR-8

Generative Adversarial Networks (GAN) boast impressive capacity to generate realistic images. However, like much of the field of deep learning, they require an inordinate amount of data to produce results, thereby limiting their usefulness in generating novelty.


08 Jan 2019

Generating Multiple Objects at Spatially Distinct Locations

ICLR 2019 tohinz/multiple-objects-gan

The object pathway focuses solely on the individual objects and is iteratively applied at the locations specified by the bounding boxes. Our experiments show that through the use of the object pathway we can control object locations within images and can model complex scenes with multiple objects at various locations.


03 Jan 2019

Improving MMD-GAN Training with Repulsive Loss Function

ICLR 2019 richardwth/MMD-GAN

Generative adversarial nets (GANs) are widely used to learn the data sampling process and their performance may heavily depend on the loss functions, given a limited computational budget. To address this issue, we propose a repulsive loss function to actively learn the difference among the real data by simply rearranging the terms in MMD.


24 Dec 2018

Generative Models from the perspective of Continual Learning

ICLR 2019 TLESORT/Generative_Continual_Learning

We investigate how several models learn and forget, considering various strategies: rehearsal, regularization, generative replay and fine-tuning. We experiment with sequential tasks on three commonly used benchmarks for Continual Learning (MNIST, Fashion MNIST and CIFAR10).


21 Dec 2018

A Style-Based Generator Architecture for Generative Adversarial Networks

12 Dec 2018rosinality/style-based-gan-pytorch

We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images (e.g., freckles, hair), and it enables intuitive, scale-specific control of the synthesis.


12 Dec 2018