arXiv:2511.15022v2 Announce Type: replace-cross Abstract: Complex-valued Gaussian primitives have recently been explored for representing holographic radiance fields in 3D novel view synthesis. In this work, we extend this line of research to the hologram optimization domain and propose a structured representation based on complex-valued 2D Gaussian primitives. Inspired by Gabor's theory, we show that our primitive attains the minimum space-frequency uncertainty and reduces the parameter search space by 5:1 compared to per-pixel parameterization. To enable end-to-end training, we develop a dif
The continuous advancements in AI and computer vision are pushing the boundaries of holographic representation and synthesis, seeking more efficient and high-fidelity methods.
This research introduces a more efficient method for computer-generated holography, potentially accelerating its development and application in fields like augmented reality, displays, and medical imaging.
The use of complex-valued 2D Gaussian primitives reduces the computational complexity and parameter space for hologram optimization, enabling more efficient end-to-end training.
- · Augmented Reality Developers
- · Holographic Display Manufacturers
- · Computer Vision Researchers
- · AI Hardware Manufacturers
- · Traditional Holography Methods
Improved efficiency in holographic content generation.
Faster development and deployment of high-quality holographic applications across various industries.
The emergence of new user interfaces and interactive experiences based on advanced holographic technology.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG