Stefan Jeschke

Stefan Jeschke
NVIDIA | Nvidia · Department of Research

PhD

About

48
Publications
13,300
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
927
Citations
Introduction
Stefan Jeschke currently works at the Department of Research, NVIDIA. Stefan does research in real-time physics simulation, Parallel Computing and Computer Graphics.
Additional affiliations
October 2016 - present
NVIDIA
Position
  • Researcher
May 2012 - present
May 2009 - April 2012
TU Wien
Position
  • PostDoc Position

Publications

Publications (48)
Article
We introduce a triangle mesh based convolutional neural network. The proposed network structure can be used for problems where input and/or output are defined on a manifold triangle mesh with or without boundary. We demonstrate its applications in cloth upsampling, adding back details to Principal Component Analysis (PCA) compressed cloth, regressi...
Article
We present a rigid body simulation method that can resolve small temporal and spatial details by using a quasi explicit integration scheme that is unconditionally stable. Traditional rigid body simulators linearize constraints because they operate on the velocity level or solve the equations of motion implicitly thereby freezing the constraint dire...
Article
The “procedural” approach to animating ocean waves is the dominant algorithm for animating larger bodies of water in interactive applications as well as in off‐line productions — it provides high visual quality with a low computational demand. In this paper, we widen the applicability of procedural water wave animation with an extension that guaran...
Article
We examine the relationship between primal, or force‐based, and dual, or constraint‐based formulations of dynamics. Variational frameworks such as Projective Dynamics have proved popular for deformable simulation, however they have not been adopted for contact‐rich scenarios such as rigid body simulation. We propose a new preconditioned frictional...
Article
Signed distance fields (SDFs) are a popular shape representation for collision detection. This is due to their query efficiency, and the ability to provide robust inside/outside information. Although it is straightforward to test points for interpenetration with an SDF, it is not clear how to extend this to continuous surfaces, such as triangle mes...
Article
Full-text available
We present a framework for the simulation of rigid and deformable bodies in the presence of contact and friction. Our method is based on a non-smooth Newton iteration that solves the underlying nonlinear complementarity problems (NCPs) directly. This approach allows us to support nonlinear dynamics models, including hyperelastic deformable bodies a...
Conference Paper
In this paper we re-examine the idea that implicit integrators with large time steps offer the best stability/performance trade-off for stiff systems. We make the surprising observation that performing a single large time step with n constraint solver iterations is less effective than computing n smaller time steps, each with a single constraint so...
Preprint
Full-text available
We present a framework for the simulation of rigid and deformable bodies in the presence of contact and friction. Our method is based on a non-smooth Newton iteration that solves the underlying nonlinear complementarity problems (NCPs) directly. This approach allows us to support nonlinear dynamics models, including hyperelastic deformable bodies a...
Preprint
Point clouds, as a form of Lagrangian representation, allow for powerful and flexible applications in a large number of computational disciplines. We propose a novel deep-learning method to learn stable and temporally coherent feature spaces for points clouds that change over time. We identify a set of inherent problems with these approaches: witho...
Article
Robustly and efficiently simulating cables and ropes that are part of a larger system such as cable driven machines, cable cars or tendons in a human or robot is a challenging task. To be able to adapt to the environment, cables are typically modeled as a large number of small segments that are connected via joints. The two main difficulties with t...
Conference Paper
We introduce a deep reinforcement learning method that learns to control articulated humanoid bodies to imitate given target motions closely when simulated in a physics simulator. The target motion, which may not have been seen by the agent and can be noisy, is supplied at runtime. Our method can recover balance from moderate external disturbances...
Article
Full-text available
The current state of the art in real-time two-dimensional water wave simulation requires developers to choose between efficient Fourier-based methods, which lack interactions with moving obstacles, and finite-difference or finite element methods, which handle environmental interactions but are significantly more expensive. This paper attempts to br...
Conference Paper
Simulating large bodies of water in real time has been a research goal for a few decades. Existing procedural approaches like FFT-based simulations typically lack dynamic response like boundary-wave reflections or general body-fluid interactions like splashes or boat wakes. On the other side of the spectrum, existing dynamic Eulerian wave simulatio...
Conference Paper
The two main constraints used in rigid body simulations are contacts and joints. Both constrain the motion of a small number of bodies in close proximity. However, it is often the case that a series of constraints restrict the motion of objects over longer distances such as the contacts in a large pile or the joints in a chain of rigid bodies. When...
Article
This paper presents a method for simulating water surface waves as a displacement field on a 2D domain. Our method relies on Lagrangian particles that carry packets of water wave energy; each packet carries information about an entire group of wave trains, as opposed to only a single wave crest. Our approach is unconditionally stable and can simula...
Article
This paper generalizes the well-known Diffusion Curves Images (DCI), which are composed of a set of Bezier curves with colors specified on either side. These colors are diffused as Laplace functions over the image domain, which results in smooth color gradients interrupted by the Bezier curves. Our new formulation allows for more color control away...
Article
We present a method to learn and propagate shape placements in 2D polygonal scenes from a few examples provided by a user. The placement of a shape is modeled as an oriented bounding box. Simple geometric relationships between this bounding box and nearby scene polygons define a feature set for the placement. The feature sets of all example placeme...
Article
Full-text available
We present an efficient wavefront tracking algorithm for animating bodies of water that interact with their environment. Our contributions include: a novel wavefront tracking technique that enables dispersion, refraction, reflection, and diffraction in the same simulation; a unique multivalued function interpolation method that enables our simulati...
Article
In this paper, we present a method for non-rigid, partial shape matching in vector graphics. Given a user-specified query region in a 2D shape, similar regions are found, even if they are non-linearly distorted. Furthermore, a non-linear mapping is established between the query regions and these matches, which allows the automatic transfer of editi...
Article
Full-text available
In this paper, we introduce a novel scene representation for the visualization of large-scale point clouds accompanied by a set of high-resolution photographs. Many real-world applications deal with very densely sampled point-cloud data, which are augmented with photographs that often reveal lighting variations and inaccuracies in registration. Con...
Article
We propose a method for propagating edit operations in 2D vector graphics, based on geometric relationship functions. These functions quantify the geometric relationship of a point to a polygon, such as the distance to the boundary or the direction to the closest corner vertex. The level sets of the relationship functions describe points with the s...
Article
This paper presents an analytic formulation for anti-aliased sampling of 2D polygons and 3D polyhedra. Our framework allows the exact evaluation of the convolution integral with a linear function defined on the polytopes. The filter is a spherically symmetric polynomial of any order, supporting approximations to refined variants such as the Mitchel...
Article
Full-text available
Capturing real-world objects with laser-scanning technology has become an everyday task. Recently, the acquisition of dynamic scenes at interactive frame rates has become feasible. A high-quality visualization of the resulting point cloud stream would require a per-frame reconstruction of object surfaces. Unfortunately, reconstruction computations...
Article
Diffusion curves are a powerful vector graphic representation that stores an image as a set of 2D Bezier curves with colors defined on either side. These colors are diffused over the image plane, resulting in smooth color regions as well as sharp boundaries. In this paper, we introduce a new automatic diffusion curve coloring algorithm. We start by...
Article
Full-text available
We present a method designed to address some limitations of typical route map displays of driving directions. The main goal of our system is to generate a printable version of a route map that shows the overview and detail views of the route within a single, consistent visual frame. Our proposed visualization provides a more intuitive spatial conte...
Article
Full-text available
We present a new Laplacian solver for minimal surfaces---surfaces having a mean curvature of zero everywhere except at some fixed (Dirichlet) boundary conditions. Our solution has two main contributions: First, we provide a robust rasterization technique to transform continuous boundary values (diffusion curves) to a discrete domain. Second, we def...
Article
Full-text available
Diffusion curve images (DCI) provide a powerful tool for efficient 2D image generation, storage and manipulation. A DCI consist of curves with colors defined on either side. By diffusing these colors over the image, the final result includes sharp boundaries along the curves with smoothly shaded regions between them. This paper extends the applicat...
Article
This paper proposes to use relief-mapped conical frusta (cones cut by planes) to skin skeletal objects. Based on this representation, current programmable graphics hardware can perform the rendering with only minimal communi- cation between the CPU and GPU. A consistent definition of conical frusta including texture parametrization and a continuous...
Article
In this paper we address the question of how to quickly model glyph-based Geographic Information System visualizations. Our solution is based on using shape grammars to set up the different aspects of a visualization, including the geometric content of the visualization, methods for resolving layout conflicts and interaction methods. Our approach s...
Article
Diffusion curve images (DCI) provide a powerful tool for efficient 2D image generation, storage and manipulation. A DCI consist of curves with colors defined on either side. By diffusing these colors over the image, the final result includes sharp boundaries along the curves with smoothly shaded regions between them. This paper extends the applicat...
Article
We present a new Laplacian solver for minimal surfaces—surfaces having a mean curvature of zero everywhere except at some fixed (Dirichlet) boundary conditions. Our solution has two main contributions: First, we provide a robust rasterization technique to transform continuous boundary values (diffusion curves) to a discrete domain. Second, we defin...
Article
In this paper we present dart throwing algorithms to generate maximal Poisson disk point sets directly on 3D surfaces. We optimize dart throwing by efficiently excluding areas of the domain that are already covered by existing darts. In the case of triangle meshes, our algorithm shows dramatic speed improvement over comparable sampling methods. The...
Article
We present a method for rendering approximate soft shadows and diffuse indirect illumination in dynamic scenes. The proposed method approximates the original scene geometry with a set of tightly fitting spheres. In previous work, such spheres have been used to dynamically evaluate the visibility function to render soft shadows. In this paper, each...
Article
Full-text available
This paper introduces a technique for rendering animated grass in real time. The technique uses front-to-back compositing of implicitly defined grass slices in a fragment shader and therefore significantly reduces the overhead associated with common vegetation rendering systems. We also introduce a texture-based animation scheme that combines globa...
Conference Paper
Full-text available
Shell mapping is a technique to represent three-dimensional surface details. This is achieved by extruding the tri- angles of an existing mesh along their normals, and mapping a 3D function (e.g., a 3D texture) into the resulting prisms. Unfortunately, such a mapping is nonlinear. Previous approaches perform a piece-wise linear approxima- tion by s...
Conference Paper
Full-text available
Shadow mapping suffers from spatial aliasing (visible as blocky shadows) as well as temporal aliasing (visible as flickering). Several methods have already been proposed for reducing such artifacts, but so far none is able to provide satisfying results in real time. This paper extends shadow mapping by reusing information of previously rasterized i...
Article
Full-text available
This paper introduces displacement mapped billboard clouds (DMBBC), a new image-based rendering primitive for the fast dis- play of geometrically complex objects at medium to far distances. The representation is based on the well-known billboard cloud (BBC) technique, which represents an object as several textured rectangles in order to dramaticall...
Conference Paper
Full-text available
This paper demonstrates the simple yet effective usage of height fields for interactive landscape visualizations using a ray casting approach implemented in the pixel shader of modern graphics cards. The rendering performance is output sensitive, i.e., it scales with the number of pixels rather than the complexity of the landscape. Given a height f...
Conference Paper
Full-text available
Impostors are image-based primitives commonly used to replace complex geometry in order to reduce the rendering time needed for displaying complex scenes. However, a big problem is the huge amount of memory required for impostors. This paper presents an algorithm that automatically places impostors into a scene so that a desired frame rate and imag...
Article
This paper gives an overview of image-based representations commonly used for reducing the geometric complex- ity of a scene description in order to accelerate the rendering process. Several different types of representations and ways for using them have been presented, which are classified and discussed here. Furthermore, the overview includes tec...
Article
Full-text available
This paper presents a procedural model for breaking ocean waves that is intended to be used for interactive visualization. The movement as well as the appearance of the waves is modelled by a set of functions in dependence of time and space. This continuous surface description allowes it to calculate all properties of every point (including foam) o...
Article
Full-text available
Impostors are image-based primitives commonly used to replace complex geometry in order to accelerate the rendering of large virtual environments. This paper de- scribes a "layered impostor technique" used for repre- senting distant scene-parts when seen from a bounded viewing region. A special layer placement is derived which bounds the geometric...
Conference Paper
Full-text available
This paper presents a new approach to generate textured depth meshes (TDMs), an impostor-based scene repre- sentation that can be used to accelerate the rendering of static polygonal models. The TDMs are precalculated for a fixed viewing region (view cell). The approach relies on a layered rendering of the scene to produce a voxel-based representat...
Conference Paper
Full-text available
This paper presents a new impostor-based approach to accelerate the rendering of very complex static scenes. The scene is partitioned into viewing regions, and a lay- ered impostor representation is precalculated for each of them. An optimal placement of impostor layers guaran- tees that our representation is indistinguishable from the original geo...
Article
This paper describes the Rectangular FishEye View for the combined presentation of 2D raster images, 2D vector graphics and text. A detailed presentation of the area of highest user interest (the focus) is integrated into a lower-detail context display providing an overview. Screen space is saved by downscaling (distorting) the context. The geometr...

Network

Cited By

Projects

Project (1)
Archived project