{"ID":2839321,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.15022","arxiv_id":"2511.15022","title":"Complex-Valued 2D Gaussian Representation for Computer-Generated Holography","abstract":"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.","short_abstract":"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-optim...","url_abs":"https://arxiv.org/abs/2511.15022","url_pdf":"https://arxiv.org/pdf/2511.15022v1","authors":"[\"Yicheng Zhan\",\"Xiangjun Gao\",\"Long Quan\",\"Kaan Akşit\"]","published":"2025-11-19T01:41:14Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.GR\",\"cs.LG\"]","methods":"[]","has_code":false}