Dr Daniele Giunchi PhD

Dr Daniele Giunchi

School of Computer Science
Assistant Professor in Scene Understanding and Smart Environments (HCI, Computer Vision, Robotics)

Contact details

Address
School of Computer Science
University of Birmingham
Edgbaston
Birmingham
B15 2TT
UK

Daniele Giunchi is Assistant Professor in Scene Understanding and Smart Environments at the University of Birmingham. My research explores intelligent interaction in immersive environments, combining VR/AR, HCI, and deep learning—focusing on vocal interfaces, multimodal systems, and neural models for perception and collaboration.

Qualifications

  • Master in Optics and Quantum Information, Sapienza University of Rome, 2023
  • Ph.D. in Computer Science (Marie Curie Fellow), University College London, 2021
  • MSc in Astronomy, University of Bologna, 2004

Biography

Daniele Giunchi is an Assistant Professor in Scene Understanding and Smart Environments at the University of Birmingham. His research focuses on immersive technologies, exploring how VR/AR, Human-Computer Interaction (HCI), and Artificial Intelligence—particularly deep learning and large language models—can enable more intuitive and adaptive user interaction. He is especially interested in vocal and multimodal interfaces for collaborative environments and perceptual scene understanding.

Daniele earned his Ph.D. in Computer Science from University College London (UCL) as a Marie Curie Fellow, where he developed neural network-based methods for artifact detection and 3D model retrieval in virtual environments. He also holds a Master’s in Optics and Quantum Information from Sapienza University of Rome, where he worked on quantum algorithms for holography, and a MSc in Astronomy from the University of Bologna, focusing on numerical simulation of cosmic structures.

His academic research is grounded in over a decade of industrial experience, having developed simulation, tracking, and 3D visualization systems in biomedical and aerospace domains. Prior to joining Birmingham, he held research roles at UCL and the CYENS Centre of Excellence, contributing to EU-funded projects on collaborative VR, smart cities, and immersive content generation.

Postgraduate supervision

AI applied to XR

Research

Daniele Giunchi’s research explores how intelligent systems can enable more natural, expressive, and adaptive interaction in extended reality (XR). His recent work focuses on the integration of large language models and speech-driven interfaces to support dynamic behavior design and real-time storytelling in immersive environments. By leveraging AI to interpret voice, gaze, and gesture, he develops advanced multimodal systems that make XR experiences more responsive and intuitive.

A central theme in his work is collaborative interaction—designing interfaces that enhance mutual awareness and coordination in distributed or co-located VR/AR settings. He investigates how behavioral cues, such as locomotion patterns and visual focus, can be used to facilitate shared understanding and narrative engagement in group tasks and exploratory scenarios.

His research also addresses the technical and design challenges of remote and asynchronous XR collaboration, building frameworks that maintain immersion and continuity across physical and virtual boundaries. Through projects that span from generative storytelling to predictive user modeling and foveated rendering, he advances the field of intelligent immersive interfaces.

Publications

Recent publications

Article

David, A, Giunchi, D, James, S, Steed, A & Esteves, A 2026, 'Exploring the Effects of Asynchronous Collaborative Art in VR with PaintBranch', SN Computer Science, vol. 7, no. 5, 456. https://doi.org/10.1007/s42979-026-04980-z

Cascarano, P, Loretti, A, Zanuttini, L, Di Pasquale, A, Hajahmadi, S, Giunchi, D, Bovo, R, Martinoni, M & Marfia, G 2026, 'Towards the target and not beyond: 2D vs 3D visual aids in MR-based neurosurgical simulation', Virtual Reality, vol. 30, no. 2, 70. https://doi.org/10.1007/s10055-026-01338-x

Wen, J, Giunchi, D, Cascarano, P, Bovo, R, Ofek, E & Steed, A 2026, 'Tuning Immersion and Performance with Adaptive Generative Music in VR', IEEE transactions on visualization and computer graphics. https://doi.org/10.1109/TVCG.2026.3679907

Steed, A, Archer, D, Brandstätter, K, Congdon, B, Friston, S, Ganapathy, P, Giunchi, D, Izzouzi, L, Woo Park, G, swapp, D & thiel, FJ 2023, 'Lessons Learned Running Distributed and Remote Mixed Reality Experiments', Frontiers in Computer Science, vol. 4, 966319. https://doi.org/10.3389/fcomp.2022.966319

Conference article

Lin, Y, Xie, T, Ma, Y, Giunchi, D, Sinclair, MJ, Je, S & Ofek, E 2026, 'GroundedReach: Enabling Body-grounded Haptic Experience in Virtual Reality with an Elbow Wearable Haptic Device', IEEE Transactions on Visualization and Computer Graphics.

Wen, J, Giunchi, D, Cascarano, P, Bovo, R, Ofek, E & Steed, A 2026, 'Tuning Immersion and Performance with Adaptive Generative Music in VR', IEEE Transactions on Visualization and Computer Graphics, vol. 32, no. 5, pp. 4280-4290. https://doi.org/10.1109/TVCG.2026.3679907

Conference contribution

Abdlkarim, D, Mukherjee, D, Giunchi, D, Di Luca, M & Ofek, E 2026, Belt and whistles - adding lower body collision awareness for MR experiences. in N Oliver, DA Shamma, H Candello, P Cesar, P Lopes, A Bozzon, T Kosch, V Liao, X Ma, V Artizzu, F Draxler, G López, AV Reinschluessel, X Tong & PO Toups Dugas (eds), CHI '26: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems., 566, Human factors in computing systems, Association for Computing Machinery , ACM CHI Conference on Human Factors in Computing Systems 2026, Barcelona, Spain, 13/04/26. https://doi.org/10.1145/3772318.3793143

Rapata, MM, Tang, J, Eslami, M, Giunchi, D, Di Luca, M, Kristensson, PO & Ofek, E 2026, Implicit Gaze+Slide: Discrete and Low-Effort Typing for Mixed Reality Using Gaze-Based Prediction and Finger Motion Refinement. in SUI '26: Proceedings of the 2026 ACM Symposium on Spatial User Interaction. Association for Computing Machinery (ACM), ACM Symposium on Spatial User Interaction, SUI 2026, Bari, Italy, 10/10/26. <https://www.youtube.com/watch?v=1V_a-HytYrw>

Wang, Z, Xie, T, Lin, Y, Zhang, X, Giunchi, D, Ofek, E & Je, S 2026, MagicPen: Enabling Dynamic Physical Scaffolding through Haptic Feedback for 3D Content Creation in VR with a Variable-length Stylus. in UIST '26: Proceedings of the 39th Annual ACM Symposium on User Interface Software and Technology. Association for Computing Machinery (ACM), 39th Annual ACM Symposium on User Interface Software and Technology, Detroit, Michigan, United States, 2/11/26. https://doi.org/10.1145/3830398.3830535

Gatti, E, Giunchi, D, Numan, N & Steed, A 2025, Around the Virtual Campfire: Early UX Insights into AI-Generated Stories in VR. in 2025 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)., 10896202, IEEE International Conference on Artificial Intelligence and Virtual Reality, Institute of Electrical and Electronics Engineers (IEEE), pp. 136-141. https://doi.org/10.1109/AIxVR63409.2025.00027

Low, HL, Giunchi, D, Bovo, R, Cascarano, P, Ritchie, N, Costanza, E & Steed, AJ 2025, Embodiment in Smartphone Augmented Reality: Effects on User Performance. in S Sorce, P Elagroudy & M Khamis (eds), Proceedings of MUM 2025 : The 24th International Conference on Mobile and Ubiquitous Multimedia, December 1st-4th. Association for Computing Machinery , pp. 291-300, 24th International Conference on Mobile and Ubiquitous Multimedia, Enna, Italy, 1/12/25. https://doi.org/10.1145/3771882.3771908

Bovo, R, Giunchi, D, Cascarano, P, Gonzalez, EJ & Franco, MG 2025, Revisiting put-that-there, context aware window interactions via LLMs. in arXiv preprint.

Cascarano, P, Loretti, A, Zanuttini, L, Giunchi, D, Bovo, R, Hajahmadi, S, Vallasciani, G, Martinoni, M & Marfia, G 2025, See It and Hear It: Multimodal Guidance in MR-Based Neurosurgical Simulation for Skill Retention. in A Batmaz, MB Machuca, F Ortega, D Zielasko, K Kim, R Skarbez, L Plabst, A Banić & M Stroppa (eds), VRST '25: Proceedings of the 2025 31st ACM Symposium on Virtual Reality Software and Technology., 26, VRST: Virtual Reality Software and Technology, Association for Computing Machinery . https://doi.org/10.1145/3756884.3766034

Giunchi, D, Numan, N, Gatti, E & Steed, A 2024, Dreamcodevr: Towards democratizing behavior design in virtual reality with speech-driven programming. in 2024 IEEE Conference Virtual Reality and 3D User Interfaces (VR). IEEE Annual International Symposium Virtual Reality, Institute of Electrical and Electronics Engineers (IEEE), pp. 579-589. https://doi.org/10.1109/VR58804.2024.00078

Friston, S, Congdon, B, Numan, N, Brandstätter, K, Izzouzi, L, Thiel, FJ, Zhang, J, Giunchi, D, Swapp, D & Steed, A 2023, Extending the Open Source Social Virtual Reality Ecosystem to the Browser in Ubiq. in A Moreno, A Jaspe-Villanueva, I Muñoz-Pandiella & J Posada (eds), Web3D '23: Proceedings of the 28th International ACM Conference on 3D Web Technology., 5, Proceedings of the International ACM Conference on 3D Web Technology, Association for Computing Machinery , pp. 1-9, The 28th International ACM Conference on 3D Web Technology, San Sebastian, Spain, 9/10/23. https://doi.org/10.1145/3611314.3615903

View all publications in research portal