Complex-Valued 2D Gaussian Representation for Computer-Generated Holography
This work addresses scalability issues in computer-generated holography systems, offering a more efficient method for hologram estimation, though it is incremental as it builds on existing representations with specific improvements.
The paper tackles the problem of high computational and memory demands in computer-generated holography by proposing a new hologram representation using complex-valued 2D Gaussian primitives, which reduces the parameter search space by up to 10:1, achieves up to 2.5x lower VRAM usage, 50% faster optimization, and higher-fidelity reconstructions.
We propose a new hologram representation based on structured complex-valued 2D Gaussian primitives, which replaces per-pixel information storage and reduces the parameter search space by up to 10:1. To enable end-to-end training, we develop a differentiable rasterizer for our representation, integrated with a GPU-optimized light propagation kernel in free space. Our extensive experiments show that our method achieves up to 2.5x lower VRAM usage and 50% faster optimization while producing higher-fidelity reconstructions than existing methods. We further introduce a conversion procedure that adapts our representation to practical hologram formats, including smooth and random phase-only holograms. Our experiments show that this procedure can effectively suppress noise artifacts observed in previous methods. By reducing the hologram parameter search space, our representation enables a more scalable hologram estimation in the next-generation computer-generated holography systems.