For the Fall 2004 semester, our seminar will be meeting every
Wednesday at 4:00 in 3403 Siebel. Many of the talks for this semester will be on
SIGGRAPH 2004 papers.
The following is a proposed schedule. If you have any conflicts with the day you're listed to give a talk, please let us know.
- Sep 15 – Lin Shi – Controllable Smoke Animation with Guiding Objects
Abstract:
This paper addresses the problem of controlling the density and dynamics of smoke (a gas phenomenon) so that the synthetic appearance of the smoke (gas) resembles a still or moving object. Both the smoke region and the target object are represented as implicit functions. As a part of the target implicit function, a shape transformation is generated between an initial smoke region and the target object. In order to match the smoke surface with the target surface, we impose carefully designed velocity constraints on the smoke boundary during a dynamic fluid simulation. The velocity constraints are derived from an iterative functional minimization procedure for shape matching. The dynamics of the smoke is formulated using a novel compressible fluid model which can effectively absorb the discontinuities in the velocity field caused by imposed velocity constraints while reproducing realistic smoke appearances. As a result, a smoke region can evolve into a regular object and follow the motion of the object while maintaining its smoke appearance.slides
- Sep 22 – Tony Kaap – Eyes for Relighting // Steve Zelinka – Mesh modelling with curve analogies
Tony Kaap:
Abstract:
Eyes for Relighting - By treating the cornea of the human eye as a parabolic reflector & lens imaging system, we can recover the lighting information around a subject from photographs by examining the light coming from the eye. Building on top of biological research and earlier work, we can use the information in an image or image sequence to recover geometry with a known light setup, or recover the light setup given a known geometry. We use this to prototype models from image sequences, and realistically light virtual objects when the original lighting is not otherwise known. slides as jpegs
Steve Zelinka:
Abstract:
Mesh Modelling With Curve Analogies - Modelling by analogy has become a useful paradigm for editing images. Using a pair of before- and after-example images of a transformation, a system that models by analogy produces analogous transformations on arbitrary new images. This paper brings the expressive power of modelling by analogy to meshes. To avoid the difficulty of specifying fully 3D example meshes, we use Curve Analogies to produce changes in meshes. We apply analogies to families of curves on an object's surface, and use the filtered curves to drive a transformation of the object. We demonstrate a range of filters, from simple local feature elimination/addition, to more general frequency enhancement filters.
- Sep 29 – Yuan Zhou – Practice talk for Vis – Pixel-Exact Rendering of Spacetime Finite Element Solutions
Abstract:
Computational simulation of time-varying physical processes
is of fundamental importance for many scientific and
engineering applications. Most frequently, time-varying
simulations are performed over multiple spatial grids at
discrete points in time. In this paper, we investigate a new
approach to time-varying simulation: spacetime
discontinuous Galerkin finite element methods. The result of
this simulation method is a simplicial tessellation of
spacetime with per-element polynomial solutions for physical
quantities such as strain, stress, and velocity. To provide
accurate visualizations of the resulting solutions, we have
developed a method for per-pixel evaluation of solution data
on the GPU. We demonstrate the importance of per-pixel
rendering versus simple linear interpolation for producing
high quality visualizations. We also show that our system
can accommodate reasonably large datasets � spacetime
meshes containing up to 6 million tetrahedra are not ncommon
in this domain.
Abstract:
Variational interpolation in curved geometries has many applications, so there has always been demand for geometrically meaningful and efficiently computable splines in manifolds. We extend the definition of the familiar cubic spline curves and splines in tension, and we show how to compute these on parametric surfaces, level sets, triangle meshes, and point samples of surfaces. This list is more comprehensive than it looks, because it includes variational motion design for animation, and allows the treatment of obstacles via barrier surfaces. All these instances of the general concept are handled by the same geometric optimization algorithm, which minimizes an energy of curves on surfaces of arbitrary dimension and codimension.
Notes in [GraphicsSeminar]/EnergyMinimizingSplinesInManifolds
Abstract:
This paper focuses on efficient rendering based on pre-computed light transport, with realistic materials and shadows under all-frequency direct lighting such as environment maps. The basic difficulty is representation and computation in the 6D space of light direction, view direction, and surface position. While image-based and synthetic methods for real-time rendering have been proposed, they do not scale to high sampling rates with variation of both lighting and viewpoint. Current approaches are therefore limited to lower dimensionality (only lighting or viewpoint variation, not both) or lower sampling rates (low frequency lighting and materials). We propose a new mathematical and computational analysis of pre-computed light transport. We use factored forms, separately pre-computing and representing visibility and material properties. Rendering then requires computing triple product integrals at each vertex, involving the lighting, visibility and BRDF. Our main contribution is a general analysis of these triple product integrals, which are likely to have broad applicability in computer graphics and numerical analysis. We first determine the computational complexity in a number of bases like point samples, spherical harmonics and wavelets. We then give efficient linear and sublinear-time algorithms for Haar wavelets, incorporating non-linear wavelet approximation of lighting and BRDFs. Practically, we demonstrate rendering of images under new lighting and viewing conditions in a few seconds, significantly faster than previous techniques.
William Baker – Stereological Techniques for Solid Textures(ACM Library) –
Stereological Techniques for Solid Textures(Robert Jagnow's page at MIT)
Abstract:
The authors present a new algorithm for generating 3D solid textures from 2D images of existing materials. This algorithm draws on techniques from stereology that have been previously developed in the fields of biology and material sciences to generate a class of solid textures that is composed of discrete macroscopic particles inside of a binding medium (such as concrete). The authors first demonstrate this approach for materials consisting only of spherical particles, and then extend their technique to include materials with particles of arbitrary shape. Side-by-side comparisons between real material and the synthetically generated material are provided to demonstrate the effectiveness of the authors� technique.
Abstract:
Using the global conformal parameterization technique introduced in (Gu, Yau, 2003) the authors construct metrics for desirable global conformal mappings (i.e. most uniform) and optimize the mappings within the space of global conformal parameterizations. They also present a method for modifying the topology of a surface to further improve the uniformity of a global conformal parameterization. Finally they show how to use optimization to selectively place the inevitable zero-points (degenerate points in the map) of the global conformal map.
My talk will first cover the key notions from (Gu, Yau, 2003), before proceeding to the optimization and topological modification techniques introduced in this paper.
- Oct 27 – Shen Dong – Mesh Repair (Ju)
Wei-Wen Feng – Context-based Surface Completion slides –
Abstract:
Analogous to 2D image completion/texture synthesis, this paper wants to complete the hole in 3D point-based model. By using octree structure, the surface is subdivided into cells and the invalid(empty) cell is filled using the example points from other cells. The main objectives of the paper are then to identify the invalid cells, to find the best-matching cell for filling the hole, and to make the points conform to neighboring points. The invalid cells are decided by testing intersection with surface. An vector-valued signature is introduced in each cell for testing the similarity and finding best-match. Finally, a method similar to Iterative Closest Point(ICP) is used to transform the points for a better conformation with neighbors.
- Nov 3 – Qing Wu – Graphcut image segmentation
"GrabCut"
Abstract:
Classical image segmentation tools use either texture (colour) information or edge (contrast) information. Recently, an approach based on optimization by graph-cut has been developed which successfully combines both types of information. In this paper we extend the graph-cut approach in three respects. First, we have developed a more powerful, iterative version of the optimisation. Secondly, the power of the iterative algorithm is used to simplify substantially the user interaction needed for a given quality of result. Thirdly, a robust algorithm for "border matting" has been developed to estimate simultaneously the alpha-matte around an object boundary and the colours of foreground pixels. We show that for moderately difficult examples the proposed method outperforms competitive tools.
Interactive Digital Photomontage
Lazy Snapping
– Eric Lorimer – 2 multi-flash papers
- Nov 10 – Okan Arikan: Radiance Caching
- Nov 17 – Confocal imaging – Matthew Graham
- Nov 24 – Thanksgiving break
Abstract:
This paper presents an inverse kinematics system based on a learned model of human poses. Given a set of constraints, our system can produce the most likely pose satisfying those constraints, in realtime. Training the model on different input data leads to different styles of IK. The model is represented as a probability distribution over the space of all possible poses. This means that our IK system can generate any pose, but prefers poses that are most similar to the space of poses in the training data. We represent the probability with a novel model called a Scaled Gaussian Process Latent Variable Model. The parameters of the model are all learned automatically; no manual tuning is required for the learning component of the system. We additionally describe a novel procedure for interpolating between styles. Our style-based IK can replace conventional IK, wherever it is used in computer animation and computer vision. We demonstrate our system in the context of a number of applications: interactive character posing, trajectory keyframing, real-time motion capture with missing markers, and posing from a 2D image.
Possible additional papers
- Simplifying Flexible Isosurfaces Using Local Geometric Measures (Vis 04)
This page
Other pages
Account
Administration