Archiv der Kategorie: Programming
Convolutional Neural Networks in PyLearn2 – Experiences with the Framework
I was working in recent days on experiments for large-scale Visual Object Classification (VOC) for Content-Based Image Retrieval (CBIR). Based on the commonly accepted high success rates of Convolutional Neural Networks (CNN), I tried to recreate Alex Krizhevsky’s Convolutional Neural Network … Weiterlesen
AMD’s Mantle API – first, bleak opinion
Due to many fuzz coming from recent developments around AMD, I found time today to review some of the very sparse material on AMD’s new Graphics API – Mantle. A good starting point for getting an overview is given via … Weiterlesen
Level-of-Detail with VTK and ParaView
I recently analysed the possibility of streamed Level-of-Detail data inside ParaView. Because Paraview builds upon VTK, I used the Computer Graphics Elements Library to build up the repective data structures. VTK itself provides 2 ways that were promising: on the … Weiterlesen
Computer Graphics Elements Library – first release
Today, I want to release a first Alpha-version of the Computer Graphics Elements library. It includes all features formerly mentioned, as well as an Octree streaming-Level-of-Detail technique. The according applications are, until this point, still excluded from the release (will be … Weiterlesen
Computer Graphics Elements Library
I, more or less proudly, announce the accomplished version of my Computer Graphics Elements Library (CGEL). The library includes: Geometric Primitive data structures (Vectors, Matrices, Vertices, Edges, Neighbourhood-Maps, Feature-Maps, Triangle Indices) with extensive attribute data support for direct Point-based Rendering … Weiterlesen
Kinect Mesher
Hey fellow friends, After a lot of hard work, the Marching Cubes Meshing Algorithm with OpenMP parallelization is done. The video show the point cloud recording of a Kinect stream. After pressing a specific key, the whole pointcloud is meshed … Weiterlesen