hidden - assigned and confirmed by the Study Dept.
Date of registration:
27.09.2018
Date of assignment:
27.09.2018
Confirmed by Study dept. on:
29.10.2018
Guidelines
As the computational power grows and rendering algorithms become more and more sophisticated, we are now able to display extremely large and complex environments. However, populating such environments with meaningful 3D data remains a tedious task. The objective of this thesis is to develop new approaches for content creation in 3D graphics leveraging recent advances in machine learning and computer vision.
References
E. Shelhamer, J. Long and T. Darrell, "Fully Convolutional Networks for Semantic Segmentation," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 4, pp. 640-651, April 1 2017. doi: 10.1109/TPAMI.2016.2572683
https://arxiv.org/abs/1411.4038