E-3DGS: Event-Based Novel View Rendering of Large-Scale Scenes Using 3D Gaussian Splatting
This addresses the problem of rendering novel views in challenging conditions like low light for applications in robotics or AR, though it is incremental as it adapts an existing technique to a new sensor type.
The paper tackles novel view synthesis for large-scale scenes using event cameras, which are more resilient to lighting and motion issues than RGB cameras, and introduces a method based on 3D Gaussian splatting that achieves 11-25% higher PSNR than EventNeRF while being much faster.
Novel view synthesis techniques predominantly utilize RGB cameras, inheriting their limitations such as the need for sufficient lighting, susceptibility to motion blur, and restricted dynamic range. In contrast, event cameras are significantly more resilient to these limitations but have been less explored in this domain, particularly in large-scale settings. Current methodologies primarily focus on front-facing or object-oriented (360-degree view) scenarios. For the first time, we introduce 3D Gaussians for event-based novel view synthesis. Our method reconstructs large and unbounded scenes with high visual quality. We contribute the first real and synthetic event datasets tailored for this setting. Our method demonstrates superior novel view synthesis and consistently outperforms the baseline EventNeRF by a margin of 11-25% in PSNR (dB) while being orders of magnitude faster in reconstruction and rendering.