AI 中文总结
PocketSplat提出一种前馈框架，通过世界空间潜在分配和精确容量控制，在移动设备上实现预算受限的高斯重建，在DL3DV和Mip-NeRF 360上达到高质量与低内存的平衡。
AI 中文摘要
移动高斯重建必须满足两个要求：重建模型必须在设备资源范围内执行，并且生成的高斯资产必须具有适合下游移动使用的表示大小。现有的前馈高斯重建器通常解码密集的、与图像对齐的候选，其最终基数由输入分辨率和视图数量隐式决定。我们提出了PocketSplat，一个用于预算受限的移动高斯资产构建的前馈框架。给定预设的输出预算，PocketSplat在预测的世界空间中组织密集的几何感知潜在候选，在局部潜在单元之间分配精确的整数容量，并仅为保留的候选解码完整的高斯属性。细胞条件潜在融合在解码前聚合重复的多视图证据，而空间责任解码在局部稀疏化后调整高斯支持。在DL3DV和分布外基准上的实验建立了相对于前馈高斯重建基线的高质量-预算权衡。在Mip-NeRF 360上，PocketSplat直接在目标iPhone上执行，并构建紧凑、更高质量的高斯资产，速度明显快于可部署的流式MVSplat变体；原生MVSplat和DepthSplat超出设备内存预算。
英文摘要
Mobile Gaussian reconstruction must satisfy two requirements: the reconstruction model must execute within a device resource envelope, and the resulting Gaussian asset must expose a representation size suited to downstream mobile use. Existing feed-forward Gaussian reconstructors commonly decode dense, image-aligned candidates whose final cardinality is implicitly determined by the input resolution and number of views. We present PocketSplat, a feed-forward framework for budgeted mobile Gaussian asset construction. Given a prescribed output budget, PocketSplat organizes dense geometry-aware latent candidates in predicted world space, allocates exact integer capacity across local latent cells, and decodes complete Gaussian attributes only for retained candidates. Cell-conditioned latent fusion aggregates repeated multi-view evidence before decoding, while spatial responsibility decoding adapts Gaussian support after local sparsification. Experiments on DL3DV and out-of-distribution benchmarks establish a strong quality--budget trade-off against feed-forward Gaussian reconstruction baselines. On Mip-NeRF 360, PocketSplat executes directly on a target iPhone and constructs compact, higher-quality Gaussian assets substantially faster than a deployable streamed MVSplat variant; native MVSplat and DepthSplat exceed the device memory budget.
