EVo: Net Shape RTM Production Line

Line and net pattern segmentation using shape modeling

Line and net patterns in a noisy environment exist in many images. Such piecewise linear patterns with a Gaussian-like profile can be differentiated from others by their distinctive shape characteristics. We propose a new algorithm for extracting lines and nets in an enhancement/thresholding type of edge operator. Line features are enhanced by second partial derivatives and segmented by thresho...

Production of near net shape components directly from CAD models

This paper presents an integrated system for the production of near net shape components based on an Octree decomposition of a 3D solid model. The Octree representation is used to automatically generate the robot instructions required to create assemblies of blocks secured by adhesive. Not only is the system capable of producing shapes of variable precision and complexity (including overhanging...

Deep Adversarial 3D Shape Net

3D object understanding and reconstruction are important research questions in computer graphics and computer vision. In graphics, researchers tried to solve this question by breaking the shape down into separate shape parts (Huang et al. (2015)). This approach has achieved plausible results in shape synthesis. However, this requires pre-processing steps, including shape segmentation and resamp...

RTM Workshop und Jalsoft

P2P-NET: Bidirectional Point Displacement Net for Shape Transform

We introduce P2P-NET, a general-purpose deep neural network which learns geometric transformations between point-based shape representations from two domains, e.g., meso-skeletons and surfaces, partial and complete scans, etc. The architecture of the P2P-NET is that of a bi-directional point displacement network, which transforms a source point set to a target point set with the same cardinalit...