GENIE：用于神经辐射场交互式编辑的高斯编码

摘要

神经辐射场（NeRF）与高斯溅射（GS）技术近期革新了三维场景表示与渲染领域。NeRF通过神经网络学习体积表示，实现了高保真的新视角合成，但其隐式编码特性使得编辑与物理交互面临挑战。相比之下，GS将场景表示为明确的高斯基元集合，支持实时渲染、更快的训练速度以及更直观的操作。这种显式结构使GS特别适合交互式编辑及与基于物理的仿真集成。本文提出GENIE（高斯编码神经辐射场交互编辑），一种混合模型，它融合了NeRF的逼真渲染质量与GS的可编辑结构化表示。我们摒弃了球谐函数用于外观建模的传统方法，转而赋予每个高斯基元一个可训练的特征嵌入。这些嵌入用于基于查询点最近k个高斯基元来条件化NeRF网络。为实现高效的条件化，我们引入了射线追踪高斯邻近搜索（RT-GPS），这是一种基于改进射线追踪管线的快速最近高斯搜索方法。同时，我们整合了多分辨率哈希网格以初始化和更新高斯特征。这些组件共同实现了实时、局部感知的编辑：当高斯基元被重新定位或修改时，其插值影响即刻反映在渲染输出中。GENIE通过结合隐式与显式表示的优势，支持直观场景操控、动态交互以及与物理仿真的兼容性，弥合了基于几何的编辑与神经渲染之间的鸿沟。代码可在(https://github.com/MikolajZielinski/genie)获取。

English

Neural Radiance Fields (NeRF) and Gaussian Splatting (GS) have recently transformed 3D scene representation and rendering. NeRF achieves high-fidelity novel view synthesis by learning volumetric representations through neural networks, but its implicit encoding makes editing and physical interaction challenging. In contrast, GS represents scenes as explicit collections of Gaussian primitives, enabling real-time rendering, faster training, and more intuitive manipulation. This explicit structure has made GS particularly well-suited for interactive editing and integration with physics-based simulation. In this paper, we introduce GENIE (Gaussian Encoding for Neural Radiance Fields Interactive Editing), a hybrid model that combines the photorealistic rendering quality of NeRF with the editable and structured representation of GS. Instead of using spherical harmonics for appearance modeling, we assign each Gaussian a trainable feature embedding. These embeddings are used to condition a NeRF network based on the k nearest Gaussians to each query point. To make this conditioning efficient, we introduce Ray-Traced Gaussian Proximity Search (RT-GPS), a fast nearest Gaussian search based on a modified ray-tracing pipeline. We also integrate a multi-resolution hash grid to initialize and update Gaussian features. Together, these components enable real-time, locality-aware editing: as Gaussian primitives are repositioned or modified, their interpolated influence is immediately reflected in the rendered output. By combining the strengths of implicit and explicit representations, GENIE supports intuitive scene manipulation, dynamic interaction, and compatibility with physical simulation, bridging the gap between geometry-based editing and neural rendering. The code can be found under (https://github.com/MikolajZielinski/genie)

GENIE：用于神经辐射场交互式编辑的高斯编码

GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing

摘要

Support