以对象为中心的2D高斯泼溅：面向紧凑对象模型的背景移除与遮挡感知剪枝
Object-Centric 2D Gaussian Splatting: Background Removal and Occlusion-Aware Pruning for Compact Object Models
AI总结：
提出利用对象掩码和遮挡感知剪枝的2D高斯泼溅方法，生成体积最多减小96%、训练快71%的紧凑对象模型，可直接用于下游应用。
摘要：
当前的Gaussian Splatting方法能有效重建整个场景，但缺乏针对特定对象的能力，导致计算成本高昂且不适用于特定对象的应用。我们提出一种利用对象掩码实现定向重建的新方法，生成以对象为中心的模型。此外，我们引入遮挡感知剪枝策略，在不牺牲质量的前提下最小化高斯数量。该方法重建的紧凑对象模型，生成的以对象为中心的高斯和网格表示比基线最多小96%、训练快71%，同时保持有竞争力的质量。这些表示无需额外处理即可直接用于外观编辑和物理模拟等下游应用。
英文摘要：
Current Gaussian Splatting approaches are effective for reconstructing entire scenes but lack the option to target specific objects, making them computationally expensive and unsuitable for object-specific applications. We propose a novel approach that leverages object masks to enable targeted reconstruction, resulting in object-centric models. Additionally, we introduce an occlusion-aware pruning strategy to minimize the number of Gaussians without compromising quality. Our method reconstructs compact object models, yielding object-centric Gaussian and mesh representations that are up to 96% smaller and up to 71% faster to train compared to the baseline while retaining competitive quality. These representations are immediately usable for downstream applications such as appearance editing and physics simulation without additional processing.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
