|
|
Automated Generation of Realistic Terrain Using Machine Learning Techniques
Střelský, Jakub ; Surynek, Pavel (advisor) ; Holan, Tomáš (referee)
Title: Automated Generation of Realistic Terrain Using Machine Learning Tech- niques Author: Jakub Střelský Department: Department of Theoretical Computer Science and Mathematical Logic Supervisor: RNDr. Pavel Surynek, Ph.D., Department of Theoretical Computer Science and Mathematical Logic Abstract: Artificial terrain is important component of computer games, simulati- ons and films. Manual terrain creation can be arduous process, hence automa- tization of this process would be convenient in many cases. Thanks to current advances in employing artifical neural networks on various generative tasks, the possibility of generating terrain using artificial neural networks should be investi- gated. We will focus on Generative Adversarial Networks as it is one of the most successful content generation method, and we will adjust this method to the task of artificial terrain generation. Resulting model is capable of generating realistic terrain based on raster sketch given by user and allows interactive modelling. Disadvantage of the model is it's requirement of a lot of training data. However, thanks to global elevation datasets providing us with more than enough training data, the model could be useful in certain applications. Keywords: procedural generation, terrain, neural networks, deep learning 1
|
|
|
Efficient implementation of deep neural networks
Kopál, Jakub ; Mrázová, Iveta (advisor) ; Střelský, Jakub (referee)
In recent years, algorithms in the area of object detection have constantly been improving. The success of these algorithms has reached a level, where much of the development is focused on increasing speed at the expense of accuracy. As a result of recent improvements in the area of deep learning and new hardware architectures optimized for deep learning models, it is possible to detect objects in an image several hundreds times per second using only embedded and mobile devices. The main objective of this thesis is to study and summarize the most important methods in the area of effective object detection and apply them to a given real-world problem. By using state-of- the-art methods, we developed a traction-by-detection algorithm, which is based on our own object detection models that track transport vehicles in real-time using embedded and mobile devices. 1
|
|
|
Intelligent Interior Design - Style Compatibility of 3D Furniture Models using Neural Networks
Sakaguchi, Yuu ; Mirbauer, Martin (advisor) ; Střelský, Jakub (referee)
Thesis title: Intelligent Interior Design - Style Compatibility of 3D Furniture Models using Neural Networks Author: Yuu Sakaguchi Abstract: Analysis of 3D shapes is a challenging task especially when it comes to measuring the styles. There are numerous possible real-world applications which benefit from machine understanding of 3D objects, so we explore analytical models to measure style-related features. 3D models can be represented in different formats such as polygon mesh, multi-view images, and point cloud, and each of them has different characteristics. In this work, we mainly focus on analyzing the ability of a point cloud to represent style information. In addition, we replicate an existing multi-view based method in order to fairly compare the performance of different representations. The goal of this thesis is to explore and evaluate point cloud based methods, and apply our method to develop applications which provides easy search in a furniture database based on style similarity. We trained and tested our model on two datasets which contain several different categories of 3D objects such as furniture in dining rooms, furniture in living rooms, buildings, and coffee sets. As the available datasets do not provide style class labels, we learn the embedding using triplet architecture and triplet...
|
|
|
Klasifikace na množinách bodů v 3D
Střelský, Jakub ; Mráz, František (advisor) ; Šikudová, Elena (referee)
Increasing interest for classification of 3D geometrical data has led to discov- ery of PointNet, which is a neural network architecture capable of processing un- ordered point sets. This thesis explores several methods of utilizing conventional point features within PointNet and their impact on classification. Classification performance of the presented methods was experimentally evaluated and com- pared with a baseline PointNet model on four different datasets. The results of the experiments suggest that some of the considered features can improve clas- sification effectiveness of PointNet on difficult datasets with objects that are not aligned into canonical orientation. In particular, the well known spin image rep- resentations can be employed successfully and reliably within PointNet. Further- more, a feature-based alternative to spatial transformer, which is a sub-network of PointNet responsible for aligning misaligned objects into canonical orientation, have been introduced. Additional experiments demonstrate that the alternative might be competitive with spatial transformer on challenging datasets. 1
|
|
|
Automated Generation of Realistic Terrain Using Machine Learning Techniques
Střelský, Jakub ; Surynek, Pavel (advisor) ; Holan, Tomáš (referee)
Title: Automated Generation of Realistic Terrain Using Machine Learning Tech- niques Author: Jakub Střelský Department: Department of Theoretical Computer Science and Mathematical Logic Supervisor: RNDr. Pavel Surynek, Ph.D., Department of Theoretical Computer Science and Mathematical Logic Abstract: Artificial terrain is important component of computer games, simulati- ons and films. Manual terrain creation can be arduous process, hence automa- tization of this process would be convenient in many cases. Thanks to current advances in employing artifical neural networks on various generative tasks, the possibility of generating terrain using artificial neural networks should be investi- gated. We will focus on Generative Adversarial Networks as it is one of the most successful content generation method, and we will adjust this method to the task of artificial terrain generation. Resulting model is capable of generating realistic terrain based on raster sketch given by user and allows interactive modelling. Disadvantage of the model is it's requirement of a lot of training data. However, thanks to global elevation datasets providing us with more than enough training data, the model could be useful in certain applications. Keywords: procedural generation, terrain, neural networks, deep learning 1
|
guest ::
