We introduce a hybrid Gaussian-hash-grid radiance representation for reconstructing 2D Gaussian scene models from multi-view images. Similar to NeST splatting, our approach reduces the entanglement between geometry and appearance common in NeRF-based models, but adds per-Gaussian latent features alongside hash-grid features to bias the optimizer toward a separation of low- and high-frequency scene components. This explicit frequency-based decomposition reduces the tendency of high-frequency texture to compensate for geometric errors. Encouraging Gaussians with hard opacity falloffs further strengthens the separation between geometry and appearance, improving both geometry reconstruction and rendering efficiency. Finally, probabilistic pruning combined with a sparsity-inducing BCE opacity loss allows redundant Gaussians to be turned off, yielding a minimal set of Gaussians sufficient to represent the scene. Using both synthetic and real-world datasets, we compare against the state of the art in Gaussian-based novel-view synthesis and demonstrate superior reconstruction fidelity with an order of magnitude fewer primitives.

翻译：我们提出一种混合高斯-哈希网格辐射场表示方法，用于从多视角图像重建二维高斯场景模型。类似于NeST散射方法，我们的方法减少了基于NeRF的模型中常见的几何与外观之间的耦合，但通过为每个高斯体添加潜在特征与哈希网格特征，引导优化器分离场景的低频与高频成分。这种基于频率的显式分解减少了高频纹理补偿几何误差的倾向。通过鼓励具有硬不透明度衰减的高斯体，进一步强化了几何与外观的分离，从而提升了几何重建质量和渲染效率。最后，结合概率剪枝与稀疏诱导的二元交叉熵不透明度损失，冗余高斯体可被关闭，得到足以表示场景的最小高斯体集合。基于合成与真实数据集的实验表明，与当前最先进的高斯体新视角合成方法相比，我们以数量级更少的图元实现了更优的重建保真度。