Complex-Valued Holographic Radiance Fields
This addresses the need for efficient, physically accurate 3D scene representations for holographic displays, representing an incremental advance in rendering technology.
The paper tackles the problem of modeling full light properties (amplitude and phase) for physically plausible rendering in holographic displays by proposing a complex-valued Gaussian representation that directly optimizes 3D scenes from RGBD multi-view images. The method achieves 30x-10,000x speed improvements compared to state-of-the-art methods while maintaining comparable image quality.
Modeling the full properties of light, including both amplitude and phase, in 3D representations is crucial for advancing physically plausible rendering, particularly in holographic displays. To support these features, we propose a novel representation that optimizes 3D scenes without relying on intensity-based intermediaries. We reformulate 3D Gaussian splatting with complex-valued Gaussian primitives, expanding support for rendering with light waves. By leveraging RGBD multi-view images, our method directly optimizes complex-valued Gaussians as a 3D holographic scene representation. This eliminates the need for computationally expensive hologram re-optimization. Compared with state-of-the-art methods, our method achieves 30x-10,000x speed improvements while maintaining on-par image quality, representing a first step towards geometrically aligned, physically plausible holographic scene representations.