Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research
Ke Li, Mana Masuda, Susanne Schmidt, Shohei Mori
2025-08-20
Summary
This paper looks at how new 3D technologies called radiance fields, like 3D Gaussian Splatting and NeRF, are changing how we create realistic virtual worlds, especially for things like virtual reality (VR) and augmented reality (AR). It also points out that even though this technology is growing fast, not many researchers are using it for VR/AR stuff yet.
What's the problem?
The problem is that even though radiance fields are really cool and could be super useful for making immersive experiences in VR and AR, there aren't many research papers connecting this new technology directly to VR and AR applications. It's hard for people in the VR/AR world to know how to use these new tools or what's already been done.
What's the solution?
To figure this out, the researchers did a big study of existing papers. They looked at lots of research that mentioned both radiance fields and VR/AR to see how people are thinking about using them, what has actually been built, and what challenges still need to be solved. They analyzed 66 specific papers that really dug into using radiance fields for VR/AR to understand the field better.
Why it matters?
This is important because it helps the VR and AR communities understand how to use these cutting-edge 3D technologies. By mapping out what's been done and what's missing, it provides a guide for future research and development, potentially speeding up innovation in creating more realistic and engaging virtual and augmented reality experiences.
Abstract
The development of radiance fields (RF), such as 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF), has revolutionized interactive photorealistic view synthesis and presents enormous opportunities for XR research and applications. However, despite the exponential growth of RF research, RF-related contributions to the XR community remain sparse. To better understand this research gap, we performed a systematic survey of current RF literature to analyze (i) how RF is envisioned for XR applications, (ii) how they have already been implemented, and (iii) the remaining research gaps. We collected 365 RF contributions related to XR from computer vision, computer graphics, robotics, multimedia, human-computer interaction, and XR communities, seeking to answer the above research questions. Among the 365 papers, we performed an analysis of 66 papers that already addressed a detailed aspect of RF research for XR. With this survey, we extended and positioned XR-specific RF research topics in the broader RF research field and provide a helpful resource for the XR community to navigate within the rapid development of RF research.