DSpace Kolekce:http://hdl.handle.net/11025/109812024-03-19T06:03:00Z2024-03-19T06:03:00ZSIFT Implementation and Optimization for General-Purpose GPUHeymann, S.Müller, K.Smolic, A.Fröhlich, B.Wiegand, T.http://hdl.handle.net/11025/110262020-07-02T08:29:55Z2007-01-01T00:00:00ZNázev: SIFT Implementation and Optimization for General-Purpose GPU
Autoři: Heymann, S.; Müller, K.; Smolic, A.; Fröhlich, B.; Wiegand, T.
Editoři: Rossignac, Jarek; Skala, Václav
Abstrakt: With the addition of free programmable components to modern graphics hardware, graphics processing units
(GPUs) become increasingly interesting for general purpose computations, especially due to utilizing parallel
buffer processing. In this paper we present methods and techniques that take advantage of modern graphics
hardware for real-time tracking and recognition of feature-points. The focus lies on the generation of feature
vectors from input images in the various stages. For the generation of feature-vectors the Scale Invariant Feature
Transform (SIFT) method [Low04a] is used due to its high stability against rotation, scale and lighting condition
changes of the processed images. We present results of the various stages for feature vector generation of our
GPU implementation and compare it to the CPU version of the SIFT algorithm. The approach works well on
Geforce6 series graphics board and above and takes advantage of new hardware features, e.g. dynamic
branching and multiple render targets (MRT) in the fragment processor [KF05]. With the presented methods
feature-tracking with real time frame rates can be achieved on the GPU and meanwhile the CPU can be used for
other tasks.2007-01-01T00:00:00ZHeymann, S.Müller, K.Smolic, A.Fröhlich, B.Wiegand, T.Fast Colorization Using Edge and Gradient ConstrainsLi, YaoLizhuang, MaDi, Wuhttp://hdl.handle.net/11025/110252020-07-02T08:29:54Z2007-01-01T00:00:00ZNázev: Fast Colorization Using Edge and Gradient Constrains
Autoři: Li, Yao; Lizhuang, Ma; Di, Wu
Editoři: Rossignac, Jarek; Skala, Václav
Abstrakt: This paper proposes a fast but effective user-guided colorization algorithm. The main difficulty with colorization
is its intensive computational cost. And the color sometimes diffuses from one region to others. We make full
use of the information given by the gray-scale images, including the edge, gradient and gradient direction, to
propagate color over regions from the user’s scribbles. We introduce a novel local distance definition which
reduces the color confusion between two regions obviously. Two-Dimensional Programming is used to get the
minimum distance from the scribbles to every pixel, and every pixel is blended by the chrominance with top
three minimum distances. This speeds up the colorization process. Our algorithm can also be extended to
recolorization and movie colorization. Experimental results show that our algorithm outperforms many state-ofthe-
art algorithms from small amount of user scribbles. Besides, the implementation require less than 1 second
on the image with 320*240 pixels.2007-01-01T00:00:00ZLi, YaoLizhuang, MaDi, WuVisual Attention for Significantly Influencing the Perception of Virtual EnvironmentsHasic, JasminkaChalmers, Alanhttp://hdl.handle.net/11025/110242020-07-02T08:29:54Z2007-01-01T00:00:00ZNázev: Visual Attention for Significantly Influencing the Perception of Virtual Environments
Autoři: Hasic, Jasminka; Chalmers, Alan
Editoři: Rossignac, Jarek; Skala, Václav
Abstrakt: The Human Visual System (HVS) is a key part of the rendering
pipeline. The human eye is only capable of sensing
image detail in a 2 foveal region, relying on rapid eye
movements, or saccades, to jump between points of interest.
These points of interest are prioritised based on the saliency
of the objects in the scene or the task the user is performing.
These ”glimpses” of a scene are then assembled by the HVS
into a coherent, but inevitably imperfect, visual perception
of the environment. In this process, much detail, which the
HVS deems unimportant, may literally go unnoticed.
In this paper we use knowledge of the HVS to influence what
our attention is attracted to in computer graphics imagery,
and thus what we actually perceive in those images. We influence
the affinity of subjects towards an object based on
the complexity of the context that object is put into. The
images are rendered using the Radiance lighting simulation
system. In this way, we are able to significantly influence
users’ preferences in an e-commerce application. Detailed
psychophysical studies are used to validate our approach.2007-01-01T00:00:00ZHasic, JasminkaChalmers, AlanGeneration of Shadows in Scene Graph based VRKuehl, BjoernBlom, Kristopher J.Beckhaus, Steffihttp://hdl.handle.net/11025/110232020-07-02T08:29:54Z2007-01-01T00:00:00ZNázev: Generation of Shadows in Scene Graph based VR
Autoři: Kuehl, Bjoern; Blom, Kristopher J.; Beckhaus, Steffi
Editoři: Rossignac, Jarek; Skala, Václav
Abstrakt: In this paper, we present our experience implementing shadows in Scene Graph based Virtual Reality systems. Shadows
are an important part of the human perception of both shape and depth and, yet, are a largely missing component in Virtual
Environments. In this work, we investigate extending standard Scene Graphs to automatically produce shadowed scenes.
This paper presents our experience embedding two popular real-time shadow methods, Shadow Mapping and Stencil Shadow
Volumes, in a popular Scene Graph system, OpenGL Performer. Our experience has shown both ways in which they can be
used and also a number of weakness in the current state of both Scene Graph systems and shadow methods. Based on our
experiences, we present suggestions for the user desiring to include shadows in their Virtual Environment and highlight areas,
where further development would benefit users significantly.2007-01-01T00:00:00ZKuehl, BjoernBlom, Kristopher J.Beckhaus, Steffi