Integrating artificial intelligence (AI) with immersive technologies represents one of the most promising frontiers in contemporary research. The increased computational power of modern GPUs has boosted the quality and polygonal density of 3D scenes. Real-time computation that can be performed by modern processors and immersive technologies such as virtual reality (VR), augmented reality (AR) and mixed reality (MR) can benefit from the creation of increasingly interactive and personalized synthetic virtual environments. Experts can use AI to speed up the development of 3D models or textures by enabling rapid prototyping of environments and scenarios. In therapeutic contexts, AI-powered VR applications can help people who have difficulty reaching medical sites and can follow therapeutic programs remotely. Additionally, neural networks, particularly convolutional neural networks (CNNs), can benefit from AI-generated synthetic photorealistic data for problems and application domains where building datasets based only on real photographs is particularly complex.
The development of these innovative applications also requires a study of innovative user interfaces to improve user interaction and immersive experience. One of the main problems of Immersive Reality software (VR, AR, and MR) is the input devices, which do not allow complete control. We are limited by joysticks, mice, keyboards, and similar devices. Innovative input systems and new user interfaces that can provide users with greater expressiveness and interaction capabilities in virtual scenarios must be investigated.
In addition, this Research Topic explores how AI – particularly modern generative models based on large language models (LLMs) – can be harnessed to develop more effective immersive applications that address complex problems (especially in education, synthetic content creation and telerehabilitation). Recent technological advancements have made these technologies more mature, with reduced costs and latency, making them increasingly accessible for broader applications. The collection will focus on how these AI models can facilitate the creation of complex immersive environments. For instance, creating textures for 3D meshes, traditionally performed manually using software like Blender or photogrammetry, is time-consuming. However, leveraging modern LLMs can accelerate this process while maintaining comparable quality. A key topic we aim to address is the rapid prototyping of 3D environments using AI, ensuring that the final output remains high quality. Moreover, AI training can be expedited by generating synthetic data within computer graphics environments. These synthetic environments allow for the creation of randomized combinations of shadows, light, and object positions, enabling the development of valuable datasets in contexts where collecting real data is challenging or hazardous. By tackling these challenges, we aim to unlock new possibilities for immersive environments that fully exploit the potential of AI.
Topics of interest include, but are not limited to, the following:
- Enhancing therapy and rehabilitation effectiveness through AI-driven VR solutions
- Studying and analyzing the impact of AI technologies on cognitive and emotional engagement in immersive learning platforms
- Integrating AI models to create multi-sensory immersive VR experiences by modulating tactile, visual and auditory outputs
- Analyzing how generative AI models can generate synthetic data in VR to speed up the object recognition pipeline
- Studying the use of AI models to populate three-dimensional environments with content (meshes, textures, sounds, texts)
- Analyzing from a human–computer interaction perspective how to implement these technologies
- Designing dynamic interfaces that adapt according to the users' behavior and their expertise in using the application, or that adapt according to their moods and emotions
- Developing new methods of interaction with virtual scenarios that allow users greater expressiveness, control, and immersiveness, also with the aid of AI
Keywords:
artificial intelligence (AI), large language models (LLMs), GPT, virtual reality (VR), mixed reality (MR), augmented reality (AR), synthetic dataset generation
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Integrating artificial intelligence (AI) with immersive technologies represents one of the most promising frontiers in contemporary research. The increased computational power of modern GPUs has boosted the quality and polygonal density of 3D scenes. Real-time computation that can be performed by modern processors and immersive technologies such as virtual reality (VR), augmented reality (AR) and mixed reality (MR) can benefit from the creation of increasingly interactive and personalized synthetic virtual environments. Experts can use AI to speed up the development of 3D models or textures by enabling rapid prototyping of environments and scenarios. In therapeutic contexts, AI-powered VR applications can help people who have difficulty reaching medical sites and can follow therapeutic programs remotely. Additionally, neural networks, particularly convolutional neural networks (CNNs), can benefit from AI-generated synthetic photorealistic data for problems and application domains where building datasets based only on real photographs is particularly complex.
The development of these innovative applications also requires a study of innovative user interfaces to improve user interaction and immersive experience. One of the main problems of Immersive Reality software (VR, AR, and MR) is the input devices, which do not allow complete control. We are limited by joysticks, mice, keyboards, and similar devices. Innovative input systems and new user interfaces that can provide users with greater expressiveness and interaction capabilities in virtual scenarios must be investigated.
In addition, this Research Topic explores how AI – particularly modern generative models based on large language models (LLMs) – can be harnessed to develop more effective immersive applications that address complex problems (especially in education, synthetic content creation and telerehabilitation). Recent technological advancements have made these technologies more mature, with reduced costs and latency, making them increasingly accessible for broader applications. The collection will focus on how these AI models can facilitate the creation of complex immersive environments. For instance, creating textures for 3D meshes, traditionally performed manually using software like Blender or photogrammetry, is time-consuming. However, leveraging modern LLMs can accelerate this process while maintaining comparable quality. A key topic we aim to address is the rapid prototyping of 3D environments using AI, ensuring that the final output remains high quality. Moreover, AI training can be expedited by generating synthetic data within computer graphics environments. These synthetic environments allow for the creation of randomized combinations of shadows, light, and object positions, enabling the development of valuable datasets in contexts where collecting real data is challenging or hazardous. By tackling these challenges, we aim to unlock new possibilities for immersive environments that fully exploit the potential of AI.
Topics of interest include, but are not limited to, the following:
- Enhancing therapy and rehabilitation effectiveness through AI-driven VR solutions
- Studying and analyzing the impact of AI technologies on cognitive and emotional engagement in immersive learning platforms
- Integrating AI models to create multi-sensory immersive VR experiences by modulating tactile, visual and auditory outputs
- Analyzing how generative AI models can generate synthetic data in VR to speed up the object recognition pipeline
- Studying the use of AI models to populate three-dimensional environments with content (meshes, textures, sounds, texts)
- Analyzing from a human–computer interaction perspective how to implement these technologies
- Designing dynamic interfaces that adapt according to the users' behavior and their expertise in using the application, or that adapt according to their moods and emotions
- Developing new methods of interaction with virtual scenarios that allow users greater expressiveness, control, and immersiveness, also with the aid of AI
Keywords:
artificial intelligence (AI), large language models (LLMs), GPT, virtual reality (VR), mixed reality (MR), augmented reality (AR), synthetic dataset generation
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.