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。与NeST泼溅类似，该方法降低了基于NeRF的模型中几何与外观之间的纠缠性，但通过为每个高斯添加潜变量特征，并结合哈希网格特征，促使优化器分离场景的高低频成分。这种显式的频率分解机制能够抑制高频纹理对几何误差的补偿倾向。通过引入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效果，从而提升几何重建质量与渲染效率。最后，结合概率剪枝与稀疏性诱导的二元交叉熵不透明度损失函数，可关闭冗余高斯体，仅保留足以表征场景的最小高斯集合。在合成与真实数据集上的实验表明，与当前最先进的高斯体新视角合成方法相比，本方法在保持一个数量级基元数量的前提下实现了更优的重建保真度。