Related papers: SharinGAN: Combining Synthetic and Real Data for U…

We present a method for synthesizing naturally looking images of multiple people interacting in a specific scenario. These images benefit from the advantages of synthetic data: being fully controllable and fully annotated with any type of…

Removing the rain streaks from single image is still a challenging task, since the shapes and directions of rain streaks in the synthetic datasets are very different from real images. Although supervised deep deraining networks have…

Supervised and unsupervised homography estimation methods depend on image pairs tailored to specific modalities to achieve high accuracy. However, their performance deteriorates substantially when applied to unseen modalities. To address…

Detecting changed regions in paired satellite images plays a key role in many remote sensing applications. The evolution of recent techniques could provide satellite images with very high spatial resolution (VHR) but made it challenging to…

While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their training. It thus became common to use available synthetic…

While developing perception based deep learning models, the benefit of synthetic data is enormous. However, performance of networks trained with synthetic data for certain computer vision tasks degrade significantly when tested on real…

Learning-based image harmonization techniques are usually trained to undo synthetic random global transformations applied to a masked foreground in a single ground truth photo. This simulated data does not model many of the important…

Artificial data synthesis is currently a well studied topic with useful applications in data science, computer vision, graphics and many other fields. Generating realistic data is especially challenging since human perception is highly…

Modern image generative models show remarkable sample quality when trained on a single domain or class of objects. In this work, we introduce a generative adversarial network that can simultaneously generate aligned image samples from…

Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions…

Realistic synthetic image data rendered from 3D models can be used to augment image sets and train image classification semantic segmentation models. In this work, we explore how high quality physically-based rendering and domain…

Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images,…

Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed by two seemingly opposed approaches: improving the realism…

We propose to harness the potential of simulation for the semantic segmentation of real-world self-driving scenes in a domain generalization fashion. The segmentation network is trained without any data of target domains and tested on the…

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…

Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data. CycleGAN was recently proposed for this problem, but critically…

Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work…

New advancements for the detection of synthetic images are critical for fighting disinformation, as the capabilities of generative AI models continuously evolve and can lead to hyper-realistic synthetic imagery at unprecedented scale 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…

Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide…