From Far and Near: Perceptual Evaluation of Crowd Representations Across Levels of Detail
This work addresses the challenge of optimizing crowd rendering for applications like games or simulations, though it appears incremental as it builds on existing LoD strategies.
The paper tackled the problem of evaluating how users perceive visual quality in crowd character representations at varying levels of detail and viewing distances, finding that different representations like geometric meshes and Neural Radiance Fields offer distinct trade-offs between fidelity and performance.
In this paper, we investigate how users perceive the visual quality of crowd character representations at different levels of detail (LoD) and viewing distances. Each representation: geometric meshes, image-based impostors, Neural Radiance Fields (NeRFs), and 3D Gaussians, exhibits distinct trade-offs between visual fidelity and computational performance. Our qualitative and quantitative results provide insights to guide the design of perceptually optimized LoD strategies for crowd rendering.