通过剔除无效特征，压缩哈希网格存储体积。
Hash Grid Feature Pruning
- 根据高斯点坐标识别并移除哈希网格中无效特征。
- 在不损失模型性能前提下，平均码率降低8%。
- 适合需要高效传输与存储的3D神经场应用。
哈希网格广泛用于高斯点阵的隐式神经场建模，既可作为熵模型的一部分，也可用于帧间预测。然而，由于3D空间中高斯点分布不规则且稀疏，导致大量区域为空，使哈希网格中存在众多无效特征，造成冗余存储与传输开销。本文提出一种哈希网格特征剪枝方法，基于输入高斯点的坐标识别并剔除无效特征，仅编码有效特征。该方法在不损害模型性能的前提下，显著降低哈希网格存储量，提升率失真性能。根据标准化委员会定义的通用测试条件（CTC），相比基线方法，平均码率降低8%。
原文摘要 · Abstract (English)
Hash grids are widely used to learn an implicit neural field for Gaussian splatting, serving either as part of the entropy model or for inter-frame prediction. However, due to the irregular and non-uniform distribution of Gaussian splats in 3D space, numerous sparse regions exist, rendering many features in the hash grid invalid. This leads to redundant storage and transmission overhead. In this work, we propose a hash grid feature pruning method that identifies and prunes invalid features based on the coordinates of the input Gaussian splats, so that only the valid features are encoded. This approach reduces the storage size of the hash grid without compromising model performance, leading to improved rate-distortion performance. Following the Common Test Conditions (CTC) defined by the standardization committee, our method achieves an average bitrate reduction of 8% compared to the baseline approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。