相关论文: Domain Stylization: A Strong, Simple Baseline for …

Domain shift is a very challenging problem for semantic segmentation. Any model can be easily trained on synthetic data, where images and labels are artificially generated, but it will perform poorly when deployed on real environments. In…

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…

Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe…

Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like…

Exploiting synthetic data to learn deep models has attracted increasing attention in recent years. However, the intrinsic domain difference between synthetic and real images usually causes a significant performance drop when applying the…

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…

In terms of Image-to-image translation, Generative Adversarial Networks (GANs) has achieved great success even when it is used in the unsupervised dataset. In this work, we aim to translate cartoon images to photo-realistic images using…

Since annotating pixel-level labels for semantic segmentation is laborious, leveraging synthetic data is an attractive solution. However, due to the domain gap between synthetic domain and real domain, it is challenging for a model trained…

The usefulness of deep learning models in robotics is largely dependent on the availability of training data. Manual annotation of training data is often infeasible. Synthetic data is a viable alternative, but suffers from domain gap. We…

Image-to-image translation has been revolutionized with GAN-based methods. However, existing methods lack the ability to preserve the identity of the source domain. As a result, synthesized images can often over-adapt to the reference…

Synthetic data generation is an appealing approach to generate novel traffic scenarios in autonomous driving. However, deep learning perception algorithms trained solely on synthetic data encounter serious performance drops when they are…

Performance on benchmark datasets has drastically improved with advances in deep learning. Still, cross-dataset generalization performance remains relatively low due to the domain shift that can occur between two different datasets. This…

Domain adaptation is of huge interest as labeling is an expensive and error-prone task, especially when labels are needed on pixel-level like in semantic segmentation. Therefore, one would like to be able to train neural networks on…

Modern deep learning models in computer vision require large datasets of real images, which are difficult to curate and pose privacy and legal concerns, limiting their commercial use. Recent works suggest synthetic data as an alternative,…

Recent advances in deep learning-based object detection techniques have revolutionized their applicability in several fields. However, since these methods rely on unwieldy and large amounts of data, a common practice is to download models…

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…

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…

Semantic segmentation networks require large amounts of pixel-level annotated data, which are costly to obtain for real-world images. Computer graphics engines can generate synthetic images alongside their ground-truth annotations. However,…

Synthetic images rendered from 3D CAD models are useful for augmenting training data for object recognition algorithms. However, the generated images are non-photorealistic and do not match real image statistics. This leads to a large…

Unsupervised transfer of object recognition models from synthetic to real data is an important problem with many potential applications. The challenge is how to "adapt" a model trained on simulated images so that it performs well on…