Related papers: Defo-Net: Learning Body Deformation using Generati…
Dark matter in the universe evolves through gravity to form a complex network of halos, filaments, sheets and voids, that is known as the cosmic web. Computational models of the underlying physical processes, such as classical N-body…
What is the right object representation for manipulation? We would like robots to visually perceive scenes and learn an understanding of the objects in them that (i) is task-agnostic and can be used as a building block for a variety of…
Generative Adversarial Networks (GANs) have become one of the dominant methods for deep generative modeling. Despite their demonstrated success on multiple vision tasks, GANs are difficult to train and much research has been dedicated…
We investigate how a residual network can learn to predict the dynamics of interacting shapes purely as an image-to-image regression task. With a simple 2d physics simulator, we generate short sequences composed of rectangles put in motion…
While standard generative adversarial networks (GANs) rely solely on training data to learn unknown probability distributions, physics-informed GANs (PI-GANs) encode physical laws in the form of stochastic partial differential equations…
Endeavors in indoor robotic navigation rely on the accuracy of segmentation models to identify free space in RGB images. However, deep learning models are vulnerable to adversarial attacks, posing a significant challenge to their real-world…
Recent work has shown that deep neural networks are highly sensitive to tiny perturbations of input images, giving rise to adversarial examples. Though this property is usually considered a weakness of learned models, we explore whether it…
While adversarial neural networks have been shown successful for static image attacks, very few approaches have been developed for attacking online image streams while taking into account the underlying physical dynamics of autonomous…
Convolutional Neural Networks (CNNs) are vulnerable to misclassifying images when small perturbations are present. With the increasing prevalence of CNNs in self-driving cars, it is vital to ensure these algorithms are robust to prevent…
If robots could reliably manipulate the shape of 3D deformable objects, they could find applications in fields ranging from home care to warehouse fulfillment to surgical assistance. Analytic models of elastic, 3D deformable objects require…
We investigate the problem of learning a probabilistic distribution over three-dimensional shapes given two-dimensional views of multiple objects taken from unknown viewpoints. Our approach called projective generative adversarial network…
Deep generative models have demonstrated great performance in image synthesis. However, results deteriorate in case of spatial deformations, since they generate images of objects directly, rather than modeling the intricate interplay of…
Generative adversarial networks have gained a lot of attention in the computer vision community due to their capability of data generation without explicitly modelling the probability density function. The adversarial loss brought by the…
Accurately predicting deformable linear object (DLO) dynamics is challenging, especially when the task requires a model that is both human-interpretable and computationally efficient. In this work, we draw inspiration from the pseudo-rigid…
A conditional general adversarial network (GAN) is proposed for image deblurring problem. It is tailored for image deblurring instead of just applying GAN on the deblurring problem. Motivated by that, dark channel prior is carefully picked…
Deformable registration is a crucial step in many medical procedures such as image-guided surgery and radiation therapy. Most recent learning-based methods focus on improving the accuracy by optimizing the non-linear spatial correspondence…
Generative Adversarial Networks (GANs) have recently achieved impressive results for many real-world applications, and many GAN variants have emerged with improvements in sample quality and training stability. However, they have not been…
Obtaining models that capture imaging markers relevant for disease progression and treatment monitoring is challenging. Models are typically based on large amounts of data with annotated examples of known markers aiming at automating…
Computed medical imaging systems require a computational reconstruction procedure for image formation. In order to recover a useful estimate of the object to-be-imaged when the recorded measurements are incomplete, prior knowledge about the…
Developing efficient time series anomaly detection techniques is important to maintain service quality and provide early alarms. Generative neural network methods are one class of the unsupervised approaches that are achieving increasing…