Project

Carousel

Goal: A project investigating embodied online dancing and partying supported by Extended Reality techniques and AI powered digital characters.

The Carousel project investigates novel, original and imaginative combinations of Artificial Intelligence and immersive interaction technologies, to allow people to feel each other’s presence, touch, and movement, even if they are not in the same physical space.

The project final goal is to help people to increase happiness by combating loneliness.

More details are available on our website : https://www.carouseldancing.org

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 101017779. Details on the support of the European Union are provided here : https://cordis.europa.eu/project/id/101017779

Date: 1 January 2021 - 31 December 2024

Updates
0 new
5
Recommendations
0 new
0
Followers
0 new
2
Reads
2 new
117

Project log

Noshaba Cheema
added 2 research items
"How can we animate 3D-characters from a movie script or move robots by simply telling them what we would like them to do?" "How unstructured and complex can we make a sentence and still generate plausible movements from it?" These are questions that need to be answered in the long-run, as the field is still in its infancy. Inspired by these problems, we present a new technique for generating compositional actions, which handles complex input sentences. Our output is a 3D pose sequence depicting the actions in the input sentence. We propose a hierarchical two-stream sequential model to explore a finer joint-level mapping between natural language sentences and 3D pose sequences corresponding to the given motion. We learn two manifold representations of the motion -- one each for the upper body and the lower body movements. Our model can generate plausible pose sequences for short sentences describing single actions as well as long compositional sentences describing multiple sequential and superimposed actions. We evaluate our proposed model on the publicly available KIT Motion-Language Dataset containing 3D pose data with human-annotated sentences. Experimental results show that our model advances the state-of-the-art on text-based motion synthesis in objective evaluations by a margin of 50%. Qualitative evaluations based on a user study indicate that our synthesized motions are perceived to be the closest to the ground-truth motion captures for both short and compositional sentences.
Noshaba Cheema
added a project reference
Pieter van der Linden
added 31 project references
Pieter van der Linden
added 5 project references
Pieter van der Linden
added an update
A full paper version has been accepted at @ICCV_2021
: "Synthesis of Compositional Animations from Textual Descriptions" -
Anindita Gosh, Noshaba Cheema , Cennet Oguz, Christian Theobald, and
 
Pieter van der Linden
added an update
At August 11 2021, the project sponsored a Bord of a Feather session at Siggraph 2021, hosted by Noshaba Cheema with the support of the other project members. To continue the exciting discussion started at this session, a Discord Server has been set up. Please feel free to join the server at : https://discord.gg/v92buKPt.
 
Pieter van der Linden
added a project goal
A project investigating embodied online dancing and partying supported by Extended Reality techniques and AI powered digital characters.
The Carousel project investigates novel, original and imaginative combinations of Artificial Intelligence and immersive interaction technologies, to allow people to feel each other’s presence, touch, and movement, even if they are not in the same physical space.
The project final goal is to help people to increase happiness by combating loneliness.
More details are available on our website : https://www.carouseldancing.org
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 101017779. Details on the support of the European Union are provided here : https://cordis.europa.eu/project/id/101017779