Laboratory for Computer
Graphics and CAD
Technion
The following program is also available in PDF format.
| Time | Speaker | Title | Abstract |
|---|---|---|---|
| 8:30 | REFRESHMENTS | ||
| 9:00 |
Dr. Margarita Osadchy Research Scientist Princeton, New Jersey, USA |
Illumination Insensitive Methods of Visual Comparison |
Image comparison is a fundamental component in many computer vision tasks such as recognition, alignment and tracking. Variation in lighting is critical to image comparison, because it dramatically affects the appearance of an object in an image. Current methods approach this problem by focusing on effects created by discontinuities in matte objects, which are insensitive to lighting changes. However this approach is very limited because it treats other effects as unmodeled noise, including the effects of smooth, untextured surfaces and the effects of shiny objects that produce significant highlights. These are present in most real objects. I show that these properties can be modeled, and they provide a rich source of information. I tackle the problem presented by smooth surfaces with no edges or texture by using a whitening tool from signal processing theory to design a superior measure of image comparison. This can provide a component in a general comparison method that also integrates past approaches. Recognition of shiny objects is also very challenging, since the appearance of the highlights they produce changes drastically with the viewing conditions. I show that using a simple qualitative model of specular reflection I can judge the consistency of specularities with 3D object geometry and use this consistency to identify very challenging transparent objects such as wine glasses. Next, I integrate this knowledge about the highlights with previous methods for matte objects. This allows recognition of glossy, smooth objects, such as pottery, which are very challenging for existing methods. |
| 9:45 |
Octavian Soldea
| Global
Curvature Analysis and Segmentation of Volumetric Data Sets Using Trivariate B-spline Functions |
This work presents a scheme to globally compute, bound, and analyze the Gaussian and mean curvature of an entire volumetric data set, using a trivariate B-spline volumetric representation. The proposed scheme is not only precise to within machine precision but also level insensitive to aliasing, compared to traditional piecewise constant volumetric data sets. Further, this scheme allows one to globally segment the images into volumetric regions with convex or concave (elliptic) iso-surfaces, planar or cylindrical (parabolic) iso-surfaces, and volumetric regions with saddle-like (hyperbolic) iso-surfaces. Being global analysis, these segmented regions are extracted simultaneously for all iso-surface level values. Results will be presented for volumetric segmentation of both the Gaussian and mean curvatures, while the introduced scheme could easily be adapted to other differential properties. *Joint work with Gershon Elber and Ehud Rivlin. |
| 10:15 |
Iddo Drori
|
Gradient Video Compositing |
We present a new framework for video compositing based on efficient cuts through similar motion and appearance followed by reconstruction of video from 3D gradients. Temporal coherence present in image sequences is utilized by cutting overlapping videos through regions in which the motion fields do not conflict and where colors are similar. The video is reconstructed by solving a Poisson equation on a 3D vector field to fuse together video regions with different color and texture. The entire process is linear in the number of pixels. We use video pairs to demonstrate the applicability and advantages of our compositing method for the operations of mixing, extending, condensing, and transitions between videos in space and time. *Joint work with
Shachar Fleishman, Daniel Cohen-Or and Yehezkel
Yeshurun |
| 10:45 | COFFEE BREAK | ||
| 11:15 |
Dotan Knaan |
Anatomical Image-Based Rigid Registration between Fluoroscopic X-ray and CT |
We describe a practical, whole system approach to rigid registration between preoperative CT and intraoperative X-rays obtained with a tracked C-arm and demonstrates its efficacy experimentally. Our approach is generic, targeted to orthopaedic surgery and includes fluoroscopic X-ray calibration, image distortion correction, optical tracking, and 2D/3D image registration. For 2D/3D image registration, we use two new gradient-based and intensity-based algorithms which are fast, robust, and accurate in realistic setups. Our experiments on simulated, in-vitro, and cadaver cases show that an overall mean target registration error of 1--1.5mm (2mm worst case), which succeeds on the first try 95\% or more of the time in less than two minutes, is practically feasible. *Joint work with L.
Joskowicz, H. Livyatan, Z. Yaniv |
| 11:45 |
Ariel Shamir |
Feature-Space
Analysis of Unstructured Meshes |
Unstructured meshes are often used in simulations and imaging applications. They provide advanced flexibility in
modeling abilities but are
more difficult to manipulate and analyze than regular
data. This work provides a novel approach for the analysis of unstructured meshes using feature-space
clustering and
feature-detection. Analyzing and revealing underlying
structures in data involve
operators on both spatial and functional domains. Slicing concentrates more on the spatial domain,
while iso-surfacing or volume-rendering concentrate more
on the functional domain. Nevertheless, many times it is
the combination of the two
domains which provides real insight on the structure of the data. In this work a combined feature-space is
defined on top of
unstructured meshes in order to search for structure in the data. A point in feature-space includes the
spatial coordinates of
the point in the mesh domain and all chosen
attributes defined on the mesh. A distance measures between
points in feature-space is defined enabling the
utilization of clustering using the mean
shift procedure (previously used for images) on
unstructured meshes. Feature space analysis is shown to be useful
for feature-extraction, for data exploration and
partitioning. |
| 12:15 |
Evgeny Lipovetsky |
An
Efficient Algorithm for the Computation of the Metric Average of Two Intersecting Convex Polygons, with Application to Morphing |
In
this work an algorithm for the computation of the metric average between
two intersecting convex polygons in 2D is developed and studied. This
algorithm has linear time complexity. As an application of this algorithm,
a new technique for morphing between two convex polygons is developed. We
produce the intermediate polygons in terms of the metric averages between
the source polygon and the target polygon mapped by a rigid motion to
intersect the source polygon, such that their intersection is large. The
new algorithm performs morphing in a non-intuitive way. In particular the
intermediate polygons are not necessarily convex.
|