Leandro Gabriel
ABSTRACT
Training a Generative Adversarial Network (GAN) involves a two-step process: training the generator network and training the discriminator network. The generator tries to generate realistic data, while the discriminator aims to distinguish between real and generated data. In this work we propose a semantic segmentation system that uses regular images for generating semantic maps through Tensor Flow framework. These maps are associated with a discrete set of tiles, which can be used for training generation of game style tile-maps. Besides the data-set creation, our solution also allows the creation of tile-maps based on image samples.
Supplemental Material
Available for Download
Analysis on detections with different settings, including changing the number of random variations, prediction probability threshold and number of threads.
- Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016).Google Scholar
- Gabriel J Brostow, Julien Fauqueur, and Roberto Cipolla. 2009. Semantic object classes in video: A high-definition ground truth database. Pattern Recognition Letters 30, 2 (2009), 88–97.Google ScholarDigital Library
- Peter J Burt, Tsai-Hong Hong, and Azriel Rosenfeld. 1981. Segmentation and estimation of image region properties through cooperative hierarchial computation. IEEE Transactions on Systems, Man, and Cybernetics 11, 12 (1981), 802–809.Google ScholarCross Ref
- Dorin Comaniciu and Peter Meer. 1997. Robust analysis of feature spaces: Color image segmentation. In Proceedings of IEEE computer society conference on computer vision and pattern recognition. IEEE, 750–755.Google ScholarCross Ref
- Pedro F Felzenszwalb and Daniel P Huttenlocher. 2004. Efficient graph-based image segmentation. International journal of computer vision 59 (2004), 167–181.Google ScholarDigital Library
- Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017).Google Scholar
- Klei Entertainment. 2013. Don’t Starve. Independent.Google Scholar
- Sanjiv Kumar and Martial Hebert. 2005. A hierarchical field framework for unified context-based classification. In Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1, Vol. 2. IEEE, 1284–1291.Google ScholarDigital Library
- Thorbjørn Lindeijer. 2008. Tiled | Flexible level editor. Thorbjørn Lindeijer. Acessed on: June 13th, 2023.Google Scholar
- Data Realms LLC. 2008. Cortex Command. Video Game. Available at: https://www.datarealms.com/.Google Scholar
- Jonathan Long, Evan Shelhamer, and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3431–3440.Google ScholarCross Ref
- McMillen, E.2011. The Binding of Isaac. Independent.Google Scholar
- Sirawan Phiphiphatphaisit and Olarik Surinta. 2020. Food image classification with improved MobileNet architecture and data augmentation. In Proceedings of the 3rd International Conference on Information Science and Systems. 51–56.Google ScholarDigital Library
- Re-Logic. 2011. Terraria. Independent.Google Scholar
- Arunpreet Sandhu, Kyle Mitchell, and Joshua McCoy. 2021. TileTerror: A System for Procedurally Generating 2D Horror Maps. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.Google Scholar
- Joseph Tighe, Marc Niethammer, and Svetlana Lazebnik. 2015. Scene parsing with object instance inference using regions and per-exemplar detectors. International Journal of Computer Vision 112 (2015), 150–171.Google ScholarDigital Library
- D. Yu and A. Hull. 2009. Spelunky. Independent.Google Scholar
- Raza Yunus, Omar Arif, Hammad Afzal, Muhammad Faisal Amjad, Haider Abbas, Hira Noor Bokhari, Syeda Tazeen Haider, Nauman Zafar, and Raheel Nawaz. 2018. A framework to estimate the nutritional value of food in real time using deep learning techniques. IEEE Access 7 (2018), 2643–2652.Google ScholarCross Ref
- Bolei Zhou, Hang Zhao, Xavier Puig, Tete Xiao, Sanja Fidler, Adela Barriuso, and Antonio Torralba. 2019. Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision 127 (2019), 302–321.Google ScholarDigital Library
Index Terms
- A Semantic Segmentation System for generating context-based tile-maps
Recommendations
Semantic Segmentation based on Stacked Discriminative Autoencoders and Context-Constrained Weakly Supervised Learning
MM '15: Proceedings of the 23rd ACM international conference on MultimediaIn this paper, we focus on tacking the problem of weakly supervised semantic segmentation. The aim is to predict the class label of image regions under weakly supervised settings, where training images are only provided with image-level labels ...
Semi- and Weakly- Supervised Semantic Segmentation with Deep Convolutional Neural Networks
MM '15: Proceedings of the 23rd ACM international conference on MultimediaSuccessful semantic segmentation methods typically rely on the training datasets containing a large number of pixel-wise labeled images. To alleviate the dependence on such a fully annotated training dataset, in this paper, we propose a semi- and weakly-...
Semantic Guided Deep Unsupervised Image Segmentation
Image Analysis and Processing – ICIAP 2019AbstractImage segmentation is an important step in many image processing tasks. Inspired by the success of deep learning techniques in image processing tasks, a number of deep supervised image segmentation algorithms have been proposed. However, ...
Comments