Related papers: Synthesizing Reality: Leveraging the Generative AI…
The standard approach to tackling computer vision problems is to train deep convolutional neural network (CNN) models using large-scale image datasets which are representative of the target task. However, in many scenarios, it is often…
Recent advances in deep learning and on-device inference could transform routine screening for skin cancers. Along with the anticipated benefits of this technology, potential dangers arise from unforeseen and inherent biases. A significant…
Our ability to synthesize sensory data that preserves specific statistical properties of the real data has had tremendous implications on data privacy and big data analytics. The synthetic data can be used as a substitute for selective real…
In this work we demonstrate that generative adversarial networks (GANs) can be used to generate realistic pervasive changes in remote sensing imagery, even in an unpaired training setting. We investigate some transformation quality metrics…
Recently, the proliferation of highly realistic synthetic images, facilitated through a variety of GANs and Diffusions, has significantly heightened the susceptibility to misuse. While the primary focus of deepfake detection has…
Learning to generate natural scenes has always been a daunting task in computer vision. This is even more laborious when generating images with very different views. When the views are very different, the view fields have little overlap or…
Developing reliable healthcare AI models requires training with representative and diverse data. In imbalanced datasets, model performance tends to plateau on the more prevalent classes while remaining low on less common cases. To overcome…
The tremendous recent advances in generative artificial intelligence techniques have led to significant successes and promise in a wide range of different applications ranging from conversational agents and textual content generation to…
Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new…
We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the…
Generative Adversarial Networks have surprising ability for generating sharp and realistic images, though they are known to suffer from the so-called mode collapse problem. In this paper, we propose a new GAN variant called Mixture Density…
Visual illusions are a very useful tool for vision scientists, because they allow them to better probe the limits, thresholds and errors of the visual system. In this work we introduce the first ever framework to generate novel visual…
Generative deep learning architectures can produce realistic, high-resolution fake imagery -- with potentially drastic societal implications. A key question in this context is: How easy is it to generate realistic imagery, in particular for…
Generative AI is transforming image synthesis, enabling the creation of high-quality, diverse, and photorealistic visuals across industries like design, media, healthcare, and autonomous systems. Advances in techniques such as…
As deep learning technology continues to evolve, the images yielded by generative models are becoming more and more realistic, triggering people to question the authenticity of images. Existing generated image detection methods detect…
While recent 3D-aware generative models have shown photo-realistic image synthesis with multi-view consistency, the synthesized image quality degrades depending on the camera pose (e.g., a face with a blurry and noisy boundary at a side…
Generative Adversarial Networks (GAN) have been widely investigated for image synthesis based on their powerful representation learning ability. In this work, we explore the StyleGAN and its application of synthetic food image generation.…
The performance of neural network models is often limited by the availability of big data sets. To treat this problem, we survey and develop novel synthetic data generation and augmentation techniques for enhancing low/zero-sample learning…
Medical image synthesis has gained a great focus recently, especially after the introduction of Generative Adversarial Networks (GANs). GANs have been used widely to provide anatomically-plausible and diverse samples for augmentation and…
As synthetic imagery is used more frequently in training deep models, it is important to understand how different synthesis techniques impact the performance of such models. In this work, we perform a thorough evaluation of the…