Generating a drawing according to a textual description

• Thesis title in Czech: Generování kresby dle slovního popisu
• Thesis title in English: Generating a drawing according to a textual description
• Key words: zpracování přirozeného jazyka, generování obrázků
• English key words: natural language processing, image generation
• Academic year of topic announcement: 2020/2021
• Thesis type: Bachelor's thesis
• Thesis language: angličtina
• Department: Institute of Formal and Applied Linguistics (32-UFAL)
• Supervisor: Mgr. Rudolf Rosa, Ph.D.
• Author: Mgr. Peter Grajcar - assigned and confirmed by the Study Dept.
• Date of registration: 26.10.2020
• Date of assignment: 26.10.2020
• Confirmed by Study dept. on: 10.11.2020
• Date and time of defence: 02.07.2021 09:00
• Date of electronic submission: 21.05.2021
• Date of submission of printed version: 27.05.2021
• Date of proceeded defence: 02.07.2021
• Opponents: Mgr. Tomáš Musil

Guidelines

The goal of the bachelor's thesis is to create a program for automatic drawing generation from a description of a scene in natural language.

Given a textual description, the program will convert the description into an intermediate structure from which the resulting drawing will be generated. The output will be a drawing which should correspond to the description.

It is sufficient to cover a limited domain of descriptions, defined e.g. by the images available in the Google Quick Draw dataset and a limited set of properties and relative positions they may have.

References

STRAKA, Milan; STRAKOVÁ, Jana. Tokenizing, pos tagging, lemmatizing and parsing ud 2.0 with udpipe. In: Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. 2017. p. 88-99.

GOOGLE. The Quick, Draw! Dataset. https://quickdraw.withgoogle.com/data

XU, Danfei, et al. Scene graph generation by iterative message passing. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. p. 5410-5419.