University College London
Browse
ARCHIVE
AGRoL-Unity.zip (106.62 MB)
ARCHIVE
StudyApp-WebGL-Unity.zip (787.02 MB)
DATASET
participant_accuracies.csv (25.61 kB)
ARCHIVE
IKRepresentations-Unity.zip (295.97 MB)
1/0
4 files

Do you read me? (E)motion Legibility of Virtual Reality Character Representations

Abstract: We compared the body movements of five VR avatar representations in a user study (N=53) to ascertain how well these representations could convey body motions associated with different emotions: One head-and-hands representation using only tracking data, one upper-body representation using inverse kinematics (IK), and three full-body representations using IK, motion-capture, and the state-of-the-art deep-learning model AGRoL. Participants emotion detection accuracies were similar for the IK and AGRoL representations, highest for the full-body motion-caupture representation and lowest for the head-and-hands representation. Our findings suggest that from the perspective of emotion expressivity, connected upper-body parts that provide visual continuity improve clarity, and that current techniques for algorithmically animating the lower-body are ineffective. In particular, the deep-learning technique studied did not produce more expressive results, suggesting the need for training data specifically made for social VR applications.

This repository contains the Unity projects for the Emotion Legibility study. Read the individual READMEs in the .zip folders for more details about each project.

AGRoL-Unity contains the AGRoL implementation with a Unity server and Python client for sending motion data from Unity to the AGRoL network and back.

IKRepresentations-Unity contains the other four avatar representations (FBMC, UBIK, FBIK, HH) and the code to animate them and create videos for the study.

StudyApp-WebGL-Unity contains the Unity project and the WebGL build for the user study. It also contains all the videos from the pre- and main study.

participant_accuracies.csv contains the participant data from the main user study.


Licenses:

AGRoL code is licensed under CC-BY-NC (parts of it are licensed under different license terms (see AGRoL Github page).

The dataset we used was "Kinematic dataset of actors expressing emotions", licensed under PhysioNet Restricted Health Data License 1.5.0.

We used the SMPL avatar model for our user study. A SMPL Unity project can be downloaded from the MPG website (login required).

SMPL-Body is licensed under the Creative Commons Attribution 4.0 International License.

Textures that were used in the Unity projects are from Kenney, CC0.

Funding

Creating Lively Interactive Populated Environments

European Commission

Find out more...

History

Usage metrics

    Department of Computer Science

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC