Share This Author
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation
- Federico Perazzi, J. Pont-Tuset, Brian McWilliams, L. Gool, M. Gross, Alexander Sorkine-Hornung
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 1 June 2016
This work presents a new benchmark dataset and evaluation methodology for the area of video object segmentation, named DAVIS (Densely Annotated VIdeo Segmentation), and provides a comprehensive analysis of several state-of-the-art segmentation approaches using three complementary metrics.
Particle-based fluid simulation for interactive applications
This paper proposes an interactive method based on Smoothed Particle Hydrodynamics (SPH) to simulate fluids with free surfaces and proposes methods to track and visualize the free surface using point splatting and marching cubes-based surface reconstruction.
Efficient simplification of point-sampled surfaces
This work has implemented incremental and hierarchical clustering, iterative simplification, and particle simulation algorithms to create approximations of point-based models with lower sampling density, and shows how local variation estimation and quadric error metrics can be employed to diminish the approximation error.
Feature Preserving Point Set Surfaces based on Non‐Linear Kernel Regression
This paper presents a novel point based surface definition combining the simplicity of implicit MLS surfaces [ SOS04, Kol05 ] with the strength of robust statistics, and reaches this new definition in terms of local kernel regression.
Meshless deformations based on shape matching
The main idea of the deformable model is to replace energies by geometric constraints and forces by distances of current positions to goal positions, determined via a generalized shape matching of an undeformed rest state with the current deformed state of the point cloud.
Algebraic point set surfaces
This paper presents a new Point Set Surface (PSS) definition based on moving least squares (MLS) fitting of algebraic spheres, and presents an novel normal estimation procedure which exploits the properties of the spherical fit for both direction estimation and orientation propagation.
Scene reconstruction from high spatio-angular resolution light fields
- Changil Kim, H. Zimmer, Y. Pritch, Alexander Sorkine-Hornung, M. Gross
- Computer ScienceACM Trans. Graph.
- 21 July 2013
This paper proposes an algorithm that leverages coherence in massive light fields by breaking with a number of established practices in image-based reconstruction, and introduces a sparse representation and a propagation scheme for reliable depth estimates which make the algorithm particularly effective for 3D input.
Multi‐scale Feature Extraction on Point‐Sampled Surfaces
Central to the method is a multi‐scale classification operator that allows feature analysis at multiplescales, using the size of the local neighborhoods as a discrete scale parameter, which significantly improves thereliability of the detection phase and makes the method more robust in the presence of noise.
Interactive Virtual Materials
This method extends the warped stiffness finite element approach for linear elasticity and combines it with a strain-state-based plasticity model and produces realistic animations of a wide spectrum of materials at interactive rates that have typically been simulated off-line thus far.
Nonlinear disparity mapping for stereoscopic 3D
- M. Lang, Alexander Sorkine-Hornung, O. Wang, Steven Poulakos, A. Smolic, M. Gross
- Computer ScienceACM Trans. Graph.
- 26 July 2010
The most important perceptual aspects of stereo vision are discussed and their implications for stereoscopic content creation are formalized into a set of basic disparity mapping operators that enable us to control and retarget the depth of a stereoscopic scene in a nonlinear and locally adaptive fashion.