Bachelor/master dissertation (Dissertations and theses)
Generating 3D Dances From Music Using Deep Neural Networks
Dupont, Elona


Full Text
Generating 3D Dances From Music Using Deep Neural Networks.pdf
Author postprint (3.14 MB)

All documents in ORBilu are protected by a user license.

Send to


Keywords :
deep learning; 3D; dance; LSTM; computer science
Abstract :
[en] This thesis focuses on the generation of original and unique 3D dances given a music using deep neural networks. A state of the art model (Dance Revolution) was adapted to take as input 3D data. Then it was trained using the recently published AIST++ dataset. At the generation phase, the model is able to generate credible dances. This was achieved by introducing a novel audio data augmentation technique that modifies the harmonic content of a song without changing the rhythmic content. This method allowed for an increase in the number of training epochs before the LSTM network converges to a static pose. Additionally, a novel method to evaluate the coherence of the generated dances with respect to the style of music is proposed. The comparison is based on key dance moves that are identified using the matrix profile. Using this method to evaluate the dances, it was found that the model generate coherent dances with respect to the dominant styles of music in the dataset.
Disciplines :
Computer science
Author, co-author :
Dupont, Elona ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > CVI2
Language :
Title :
Generating 3D Dances From Music Using Deep Neural Networks
Defense date :
June 2021
Institution :
Unilu - University of Luxembourg, Luxembourg
Degree :
Master in Information and Computer Sciences
Promotor :
Available on ORBilu :
since 03 March 2022


Number of views
198 (13 by Unilu)
Number of downloads
272 (15 by Unilu)


Similar publications

Contact ORBilu