Skip to main content

Research Repository

Advanced Search

Outputs (9)

DeFT-Net: Dual-Window Extended Frequency Transformer for Rhythmic Motion Prediction (2024)
Presentation / Conference Contribution
Ademola, A., Sinclair, D., Koniaris, B., Hannah, S., & Mitchell, K. (2024, September). DeFT-Net: Dual-Window Extended Frequency Transformer for Rhythmic Motion Prediction. Presented at EG UK Computer Graphics & Visual Computing (2024), London, UK

Enabling online virtual reality (VR) users to dance and move in a way that mirrors the real-world necessitates improvements in the accuracy of predicting human motion sequences paving way for an immersive and connected experience. However, the drawba... Read More about DeFT-Net: Dual-Window Extended Frequency Transformer for Rhythmic Motion Prediction.

DanceMark: An open telemetry framework for latency sensitive real-time networked immersive experiences (2024)
Presentation / Conference Contribution
Koniaris, B., Sinclair, D., & Mitchell, K. (2024, March). DanceMark: An open telemetry framework for latency sensitive real-time networked immersive experiences. Presented at IEEE VR Workshop on Open Access Tools and Libraries for Virtual Reality, Orlando, FL

DanceMark is an open telemetry framework designed for latency-sensitive real-time networked immersive experiences, focusing on online dancing in virtual reality within the DanceGraph platform. The goal is to minimize end-to-end latency and enhance us... Read More about DanceMark: An open telemetry framework for latency sensitive real-time networked immersive experiences.

MoodFlow: Orchestrating Conversations with Emotionally Intelligent Avatars in Mixed Reality (2024)
Presentation / Conference Contribution
Casas, L., Hannah, S., & Mitchell, K. (2024, March). MoodFlow: Orchestrating Conversations with Emotionally Intelligent Avatars in Mixed Reality. Presented at ANIVAE 2024 : 7th IEEE VR Internal Workshop on Animation in Virtual and Augmented Environments, Orlando, Florida

MoodFlow presents a novel approach at the intersection of mixed reality and conversational artificial intelligence for emotionally intelligent avatars. Through a state machine embedded in user prompts, the system decodes emotional nuances, enabling a... Read More about MoodFlow: Orchestrating Conversations with Emotionally Intelligent Avatars in Mixed Reality.

Design Considerations of Voice Articulated Generative AI Virtual Reality Dance Environments (2024)
Presentation / Conference Contribution
Casas, L., Mitchell, K., Tamariz, M., Hannah, S., Sinclair, D., Koniaris, B., & Kennedy, J. (2024, May). Design Considerations of Voice Articulated Generative AI Virtual Reality Dance Environments. Presented at SIGCHI GenAI in UGC Workshop, Honolulu, Hawaii

We consider practical and social considerations of collaborating verbally with colleagues and friends, not confined by physical distance, but through seamless networked telepresence to interactively create shared virtual dance environments. In respon... Read More about Design Considerations of Voice Articulated Generative AI Virtual Reality Dance Environments.

Method and system for visually seamless grafting of volumetric data (2024)
Patent
Mitchell, K. J. (2024). Method and system for visually seamless grafting of volumetric data

Visually seamless grafting of volumetric data. In some implementations, a method includes obtaining volumetric data that represents a first volume including one or more three-dimensional objects. Planar slices of the first volume are determined and f... Read More about Method and system for visually seamless grafting of volumetric data.

Expressive Talking Avatars (2024)
Journal Article
Pan, Y., Tan, S., Cheng, S., Lin, Q., Zeng, Z., & Mitchell, K. (2024). Expressive Talking Avatars. IEEE Transactions on Visualization and Computer Graphics, 30(5), 2538-2548. https://doi.org/10.1109/TVCG.2024.3372047

Stylized avatars are common virtual representations used in VR to support interaction and communication between remote collaborators. However, explicit expressions are notoriously difficult to create, mainly because most current methods rely on geome... Read More about Expressive Talking Avatars.