Complex-Valued Holographic Radiance Fields
By: Yicheng Zhan , Dong-Ha Shin , Seung-Hwan Baek and more
Potential Business Impact:
Creates realistic 3D holograms much faster.
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.
Similar Papers
Complex-Valued 2D Gaussian Representation for Computer-Generated Holography
CV and Pattern Recognition
Makes holograms better and faster to create.
Real-time 3D Visualization of Radiance Fields on Light Field Displays
Graphics
Shows 3D worlds smoothly on special screens.
HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis
CV and Pattern Recognition
Makes 3D scenes look real with less space.