隐式表示已死！显式基元万岁！
Implicit representations are dead. Long live explicit primitives!
- Technical University Munich（慕尼黑工业大学）
- University of Zurich（苏黎世大学）
- Imperial College London（伦敦帝国学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对医学影像，对比评估了高斯显式基元与隐式神经表示，发现高斯表示重建性能相当或更优，且计算成本更低，有望成为医学影像领域的研究方向。
AI中文摘要：
医学数据的连续参数化已成为一种强大的范式，用于生成与分辨率无关的图像表示。尽管隐式神经表示提供了高保真度和紧凑存储，但它们依赖全局多层感知机（Multi-Layer Perceptrons），会产生可观的计算成本、大量内存需求以及漫长的优化时间。随着医学影像向更精细、高分辨率的体积数据发展，这些成本给隐式方法的适用性带来了重大瓶颈。近来，基于高斯的显式基元通过将深度网络的计算替换为本地化、适配光栅化的基元，彻底改变了表示学习范式。本文针对医学影像应用，对高斯表示与隐式方法开展了全面的跨维度评估。首先，我们概述了显式基元所具备的数学特性，这些特性超出了隐式神经范式的能力范围。随后，我们在两个高要求图像数据集上对计算性能进行了基准测试：2D显微组织学和3D肺部计算机断层扫描（Computed Tomography, CT）。实验表明，在所有压缩因子下，高斯表示的重建指标始终与隐式方法相当或更优，同时优化时间和内存需求显著更低。结合显式基元具备的引人注目的数学特性，这些发现推动了高斯表示的更广泛采用，并使其成为医学影像领域未来研究的有吸引力的方向。
英文摘要：
Continuous parameterization of medical data has emerged as a powerful paradigm for resolution-independent image representation. While Implicit Neural Representations offer high fidelity and compact storage, their reliance on global Multi-Layer Perceptrons incurs sizeable computational costs, large memory requirements, and extensive optimization times. As medical imaging trends towards ever-more detailed, high-resolution volumes, these costs impose significant bottlenecks in the applicability of implicit approaches. Recently, explicit Gaussian-based primitives have revolutionized the representation learning paradigm by trading deep network evaluations for localized, rasterization-friendly primitives. In this paper, we present a comprehensive, cross-dimensional evaluation of Gaussian representations against implicit approaches for medical imaging applications. First, we outline a theoretical overview on the mathematical properties offered by explicit primitives beyond what is capable under the implicit neural paradigm. Subsequently, we benchmark the computational performance on two demanding image datasets: 2D microscopy histology and 3D lung Computed Tomography (CT). Our experiments demonstrate that Gaussian representations consistently match or surpass reconstruction metrics compared to implicit methods across all compression factors, while displaying significantly lower optimization times, and memory requirements. Together with the compelling mathematical properties offered by explicit primitives, these findings motivate the wider adoption of Gaussian representations and position them as an attractive direction for future research in medical imaging.
