Evaluating CrowdSplat: Perceived Level of Detail for Gaussian Crowds
This addresses the need for efficient and realistic crowd rendering in real-time graphics applications like VR and games, but it is incremental as it builds on existing 3D Gaussian Splatting methods.
The paper tackled the problem of determining the perceived quality of 3D Gaussian avatars for crowd rendering by conducting a two-alternative forced choice experiment, finding that factors like motion, number of Gaussians, and avatar height affect detail perception to inform LOD optimization.
Efficient and realistic crowd rendering is an important element of many real-time graphics applications such as Virtual Reality (VR) and games. To this end, Levels of Detail (LOD) avatar representations such as polygonal meshes, image-based impostors, and point clouds have been proposed and evaluated. More recently, 3D Gaussian Splatting has been explored as a potential method for real-time crowd rendering. In this paper, we present a two-alternative forced choice (2AFC) experiment that aims to determine the perceived quality of 3D Gaussian avatars. Three factors were explored: Motion, LOD (i.e., #Gaussians), and the avatar height in Pixels (corresponding to the viewing distance). Participants viewed pairs of animated 3D Gaussian avatars and were tasked with choosing the most detailed one. Our findings can inform the optimization of LOD strategies in Gaussian-based crowd rendering, thereby helping to achieve efficient rendering while maintaining visual quality in real-time applications.