相关论文: A simple prescription for simulating and character…
We present a mathematical and algorithmic scheme for learning the principal geometric elements in an image or 3D object. We build on recent work that convexifies the basic problem of finding a combination of a small number shapes that…
Implicit Neural Representations (INR) have been successfully employed for Arbitrary-scale Super-Resolution (ASR). However, INR-based models need to query the multi-layer perceptron module numerous times and render a pixel in each query,…
Grasping objects of different shapes and sizes - a foundational, effortless skill for humans - remains a challenging task in robotics. Although model-based approaches can predict stable grasp configurations for known object models, they…
In order to manipulate a deformable object, such as rope or cloth, in unstructured environments, robots need a way to estimate its current shape. However, tracking the shape of a deformable object can be challenging because of the object's…
We develop a method to enable collaborative modelling of gravitational lenses and lens candidates, that could be used by non-professional lens enthusiasts. It uses an existing free-form modelling program (glass), but enables the input to…
The aim of this paper is to present a new method of approximation of planar data set using only arcs or segments. The first problem we are trying to solve is the following: the CNC machines can work only with simple curves (arcs or…
Object compositing based on 2D images is a challenging problem since it typically involves multiple processing stages such as color harmonization, geometry correction and shadow generation to generate realistic results. Furthermore,…
Many real-world materials are characterized by a glittery appearance. Reproducing this effect in physically based renderings is a challenging problem due to its discrete nature, especially in real-time applications which require a…
We use a new non-parametric gravitational modelling tool -- \Glass{} -- to determine what quality of data (strong lensing, stellar kinematics, and/or stellar masses) are required to measure the circularly averaged mass profile of a lens and…
The fidelity of relighting is bounded by both geometry and appearance representations. For geometry, both mesh and volumetric approaches have difficulty modeling intricate structures like 3D hair geometry. For appearance, existing…
Reconstructing articulated objects prevalent in daily environments is crucial for applications in augmented/virtual reality and robotics. However, existing methods face scalability limitations (requiring 3D supervision or costly…
As engineered systems grow in complexity, there is an increasing need for automatic methods that can detect, diagnose, and even correct transient anomalies that inevitably arise and can be difficult or impossible to diagnose and fix…
Using simple, intuitive arguments, we discuss the expected accuracy with which astrophysical parameters can be extracted from an observed gravitational wave signal. The observation of a chirp like signal in the data allows for measurement…
Images of the eye are key in several computer vision problems, such as shape registration and gaze estimation. Recent large-scale supervised methods for these problems require time-consuming data collection and manual annotation, which can…
This paper introduces the geodesics of triangulated image object shapes. Both rectilinear and curvilinear triangulations of shapes are considered. The triangulation of image object shapes leads to collections of what are known as nerve…
Unsupervised learning algorithms are beginning to achieve accuracies comparable to their supervised counterparts on benchmark computer vision tasks, but their utility for practical applications has not yet been demonstrated. In this work,…
Studies of weak gravitational lensing by large-scale structures require the measurement of the distortions introduced to the shapes of distant galaxies at the few percent level by anisotropic light deflection along the line of sight. To…
Although human reconstruction typically results in human-specific avatars, recent 3D scene reconstruction techniques utilizing pixel-aligned features show promise in generalizing to new scenes. Applying these techniques to human avatar…
Aerodynamic shape optimization has many industrial applications. Existing methods, however, are so computationally demanding that typical engineering practices are to either simply try a limited number of hand-designed shapes or restrict…
The frequency of giant arcs - highly distorted and strongly gravitationally lensed background galaxies - is a powerful test for cosmological models. Previous comparisons of arc statistics for the currently favored concordance cosmological…