This thesis aims to explore the opportunities of voxel modeling with Machine Learning. First, it introduces (1) what voxel modeling is, compared to traditional model technic, what the characteristics of voxel model such as pixel map and graph representation, and what the Deep Learning and network are. The thesis examines (2) prototypical implementations of proposed design systems or workflows based on the process from rasterization of space and geometry to Machine Learning.
scene parsing , semantic segmentation, colorization Learning Deep Features for Scene Recognition DeepStereo: Learning to Predict New Views from the World's Imagery Data-driven Visual Similarity for Cross-domain Image Matching Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial ModelingNext!
How they construct: Define mathematical model for curves or surfaces Data: Control points, Knot vector, and Positional, tangential and curvature continuity
voxel & pixel dense representation continuous information implicit relations due to proximity [neighbors] Mesh (graph like structure) sparse representation discrete points or information explicit relations
- Pixel is point like feature, this pixelated grid carries the information and help to do position. - the idea pixelated or voxelated space allows describe properties that derived by point to point in space.
- Voxel could be considered as a set of image(pixel)
Voxel is a 3 dimensional grid containing pixels can have rich data set including R, G, B, A values.
It is frequently utilized for visualization of scientific or medical data which is needed for volumetric representation.
Voxel for geometry in space is a discretized space of geometry
where it has a beam or node are connecting but as a continuous map in space.
This is basically an idea that an object become a 3 dimensional map.
train : 3,200 images (random) validation : 800 images (random) optimization Adam Optimizer Gradient Descent Optimizer Momentum Optimizer Proximal Gradient Descent Optimizer Ftrl Optimizer RMSProp OptimizerNext!
class : 13
train images : 13,000 images
one iteration : 100 images
epoch : 1400 iterations
total iteration : 140,000
network : originated from alexNet
learning rate = 0.01
f(a,b, blend ) = a (1.0 - blend ) + b * blend
f(a,b) = ab
f(a,b) = 1 - ( 1 - a ) ( 1 - b )
f(a,b) = 2ab , if a < 0.5
f(a,b) = 1 - 2 ( 1 - a ) ( 1 - b ) , if a > 0.5
f(a,b) = 2ab + a^2 (1 - 2b) , if a < 0.5
f(a,b) = 2a (1-b) + sqrt(a) ( 2b - 1) , if a > 0.5