arXiv research

AR-GANs learn depth and DoF from unlabeled images using aperture rendering and focus cues.

Study on deep learning for speckle noise reduction in imaging modalities.

In this article, we analyze the microlocal properties of the linearized forward scattering operator $F$ and the normal operator $F^{*}F$ (where $F^{*}$ is the $L^{2}$ adjoint of $F$) which arises in Synthetic Aperture Radar imaging for the common midpoint acquisition geometry. When $F^{*}$ is applied to the scattered d…

We establish a link between Fourier optics and a recent construction from the machine learning community termed the kernel mean map. Using the Fraunhofer approximation, it identifies the kernel with the squared Fourier transform of the aperture. This allows us to use results about the invertibility of the kernel mean m…

Synthetic aperture sonar (SAS) imagery can generate high resolution images of the seafloor. Thus, segmentation algorithms can be used to partition the images into different seafloor environments. In this paper, we compare two possibilistic segmentation approaches. Possibilistic approaches allow for the ability to detec…

Kernel K-means clusters probability distributions.

Deep learning applied to SAR data is explored in this paper.

Study shows latent space OOD detection isn't a reliable proxy for model performance.

Radio frequency (RF) sensors are used alongside other sensing modalities to provide rich representations of the world. Given the high variability of complex-valued target responses, RF systems are susceptible to attacks masking true target characteristics from accurate identification. In this work, we evaluate differen…

We address the issue of edge detection in Synthetic Aperture Radar imagery. In particular, we propose nonparametric methods for edge detection, and numerically compare them to an alternative method that has been recently proposed in the literature. Our results show that some of the proposed methods display superior res…

Paper tackles anomaly detection in SAR images without labeled data.

For any given $C^\infty$ immersion ${\bf r}: S^1\to \mathbb{R}^2$ such that the set $\mathcal{NS}_{\bf r}=\mathbb{R}^2-\cup_{s\in S^1}\left({\bf r}(s)+d{\bf r}_{s}(T_s(S^1))\right)$ is not empty, a simple geometric model of crystal growth is constructed. It is shown that our geometric model of crystal growth never form…

This paper develops a cohomological hierarchy for bistable visual paradoxes.

Automates hair color digitization using imaging and deep learning.

A neural scene representation framework enforcing 3D transformations.

New $k$-means method clusters radar image sequences using SPD matrices.

We present the OpenAI Remote Rendering Backend (ORRB), a system that allows fast and customizable rendering of robotics environments. It is based on the Unity3d game engine and interfaces with the MuJoCo physics simulation library. ORRB was designed with visual domain randomization in mind. It is optimized for cloud de…

We perform an optimal localization of asymptotically flat initial data sets and construct data that have positive ADM mass but are exactly trivial outside a cone of arbitrarily small aperture. The gluing scheme that we develop allows to produce a new class of $N$-body solutions for the Einstein equation, which patently…

We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple supervision. The setting is significant since tuple supervision is costly and sometimes eve…

We create real-time geodesic rendering for non-isotropic geometries.

Interferometric Synthetic Aperture Radar (InSAR) imagery for estimating ground movement, based on microwaves reflected off ground targets is gaining increasing importance in remote sensing. However, noise corrupts microwave reflections received at satellite and contaminates the signal's wrapped phase. We introduce Conv…

Interferometric Synthetic Aperture Radar (InSAR) imagery based on microwaves reflected off ground targets is becoming increasingly important in remote sensing for ground movement estimation. However, the reflections are contaminated by noise, which distorts the signal's wrapped phase. Demarcation of image regions based…

ROOTS learns to represent and render 3D scenes with object-centric models.

This paper improves anomaly detection in lane rendering images for safer navigation.

DVAO predicts volumetric ambient occlusion for real-time volume rendering.

Understanding the 3-dimensional structure of the world is a core challenge in computer vision and robotics. Neural rendering approaches learn an implicit 3D model by predicting what a camera would see from an arbitrary viewpoint. We extend existing neural rendering to more complex, higher dimensional scenes than previo…

NeRF-VAE generates 3D scenes with geometric structure from few images.

We study the evolution of complete non-compact convex hypersurfaces in $\mathbb{R}^{n+1}$ by the inverse mean curvature flow. We establish the long time existence of solutions and provide the characterization of the maximal time of existence in terms of the tangent cone at infinity of the initial hypersurface. Our proo…

Many machine learning image classifiers are vulnerable to adversarial attacks, inputs with perturbations designed to intentionally trigger misclassification. Current adversarial methods directly alter pixel colors and evaluate against pixel norm-balls: pixel perturbations smaller than a specified magnitude, according t…

We present an approach for polarimetric Synthetic Aperture Radar (SAR) image region boundary detection based on the use of B-Spline active contours and a new model for polarimetric SAR data: the GHP distribution. In order to detect the boundary of a region, initial B-Spline curves are specified, either automatically or…

Importance sampling is one of the most widely used variance reduction strategies in Monte Carlo rendering. In this paper, we propose a novel importance sampling technique that uses a neural network to learn how to sample from a desired density represented by a set of samples. Our approach considers an existing Monte Ca…

Improves spline quality and accuracy in computational microscopy.

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 effectiveness of several different synthesis techniques and their impact on the complexity o…

We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algor…

Semi-supervised learning algorithms reduce the high cost of acquiring labeled training data by using both labeled and unlabeled data during learning. Deep Convolutional Networks (DCNs) have achieved great success in supervised tasks and as such have been widely employed in the semi-supervised learning. In this paper we…

We present a technique for efficiently synthesizing images of atmospheric clouds using a combination of Monte Carlo integration and neural networks. The intricacies of Lorenz-Mie scattering and the high albedo of cloud-forming aerosols make rendering of clouds---e.g. the characteristic silverlining and the "whiteness" …

3D adversarial logos can fool object detectors in real-world settings.

Polarimetric Synthetic Aperture Radar (PolSAR) images are establishing as an important source of information in remote sensing applications. The most complete format this type of imaging produces consists of complex-valued Hermitian matrices in every image coordinate and, as such, their visualization is challenging. Th…

We explore a new domain of learning to infer user interface attributes that helps developers automate the process of user interface implementation. Concretely, given an input image created by a designer, we learn to infer its implementation which when rendered, looks visually the same as the input image. To achieve thi…

In this study we investigate the potential for using synthetic aperture radar (SAR) data to provide high resolution defoliation and regrowth mapping of trees in the tundra-forest ecotone. Using aerial photographs, four areas with live forest and four areas with dead trees were identified. Quad-polarimetric SAR data fro…

Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications. However, recent studies show that DNNs are vulnerable to adversarial examples, which are carefully crafted inputs aiming to mislead the predictions. Currently, the majority of these studies have focused on per…

This paper presents a new approach for filter design based on stochastic distances and tests between distributions. A window is defined around each pixel, samples are compared and only those which pass a goodness-of-fit test are used to compute the filtered value. The technique is applied to intensity Synthetic Apertur…

Improved person detection in occluded conditions with AOS images.

In this paper we present Percival, a browser-embedded, lightweight, deep learning-powered ad blocker. Percival embeds itself within the browser's image rendering pipeline, which makes it possible to intercept every image obtained during page execution and to perform blocking based on applying machine learning for image…

Even as deep neural networks (DNNs) have achieved remarkable success on vision-related tasks, their performance is brittle to transformations in the input. Of particular interest are semantic transformations that model changes that have a basis in the physical world, such as rotations, translations, changes in lighting…

Algorithm finds optimal affine transformation to minimize overall distortion.

Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is where graphics engines may come in handy since they abstract away low-level detail…

Deep Learning is gaining traction with geophysics community to understand subsurface structures, such as fault detection or salt body in seismic data. This study describes using deep learning method for iceberg or ship recognition with synthetic aperture radar (SAR) data. Drifting icebergs pose a potential threat to ac…