SparseSplat：面向可应用的像素非对齐预测前馈三维高斯泼溅
SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction
用熵驱动的概率采样按局部纹理丰富度自适应决定高斯密度，并配合点云网络编码局部上下文，可直接用于需要紧凑 3DGS 表示的下游重建与实时渲染管线。
原文依据 we propose entropy-based probabilistic sampling, generating large, sparse Gaussians in textureless areas
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期前馈三维高斯泼溅（3DGS）的进展显著提升了渲染质量。然而，以往前馈 3DGS 方法所生成的空间均匀且高度冗余的 3DGS 地图，限制了其与下游重建任务的集成。我们提出 SparseSplat，这是首个根据场景结构和局部区域信息丰富度自适应调整高斯密度的前馈 3DGS 模型，可生成高度紧凑的 3DGS 地图。为此，我们提出基于熵的概率采样，在无纹理区域生成大而稀疏的高斯，并将小而密集的高斯分配给信息丰富的区域。此外，我们设计了一个专用的点云网络，能够高效编码局部上下文并将其解码为 3DGS 属性，从而解决通用 3DGS 优化流程与前馈模型之间感受野不匹配的问题。大量实验结果表明，SparseSplat 仅用 22% 的高斯即可达到最优的渲染质量，并且仅用 1.5% 的高斯仍能保持合理的渲染质量。
英文原文摘要 1132 字符
Recent progress in feed-forward 3D Gaussian Splatting (3DGS) has notably improved rendering quality. However, the spatially uniform and highly redundant 3DGS map generated by previous feed-forward 3DGS methods limits their integration into downstream reconstruction tasks. We propose SparseSplat, the first feed-forward 3DGS model that adaptively adjusts Gaussian density according to scene structure and information richness of local regions, yielding highly compact 3DGS maps. To achieve this, we propose entropy-based probabilistic sampling, generating large, sparse Gaussians in textureless areas and assigning small, dense Gaussians to regions with rich information. Additionally, we designed a specialized point cloud network that efficiently encodes local context and decodes it into 3DGS attributes, addressing the receptive field mismatch between the general 3DGS optimization pipeline and feed-forward models. Extensive experimental results demonstrate that SparseSplat can achieve state-of-the-art rendering quality with only 22% of the Gaussians and maintain reasonable rendering quality with only 1.5% of the Gaussians.