Perceptual-GS：面向高斯泼溅的场景自适应感知致密化
Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
AI总结：
针对3DGS难以自适应优化高斯分布的问题，提出Perceptual-GS，将感知灵敏度融入训练，通过感知感知表示和自适应分布提升重建质量与效率，在多个数据集上达到最先进性能。
摘要：
三维高斯泼溅（3D Gaussian Splatting, 3DGS）已成为新视角合成的一种强大技术。然而，现有方法难以根据场景特征自适应地优化高斯原语的分布，这使得在重建质量与效率之间取得平衡颇具挑战。受人类感知的启发，我们提出了面向高斯泼溅的场景自适应感知致密化方法（Perceptual-GS），这是一种将感知灵敏度融入3DGS训练过程的新框架，以应对上述挑战。我们首先引入一种感知感知表示，该表示在约束高斯原语数量的同时，对人类视觉灵敏度进行建模。在此基础之上，我们开发了一种感知灵敏度自适应分布，为视觉关键区域分配更精细的高斯粒度，从而提升重建质量与鲁棒性。在包括用于大规模场景的BungeeNeRF在内的多个数据集上的广泛评估表明，Perceptual-GS在重建质量、效率与鲁棒性方面均达到了最先进的性能。代码已公开于：https://github.com/eezkni/Perceptual-GS
英文摘要：
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis. However, existing methods struggle to adaptively optimize the distribution of Gaussian primitives based on scene characteristics, making it challenging to balance reconstruction quality and efficiency. Inspired by human perception, we propose scene-adaptive perceptual densification for Gaussian Splatting (Perceptual-GS), a novel framework that integrates perceptual sensitivity into the 3DGS training process to address this challenge. We first introduce a perception-aware representation that models human visual sensitivity while constraining the number of Gaussian primitives. Building on this foundation, we develop a perceptual sensitivity-adaptive distribution to allocate finer Gaussian granularity to visually critical regions, enhancing reconstruction quality and robustness. Extensive evaluations on multiple datasets, including BungeeNeRF for large-scale scenes, demonstrate that Perceptual-GS achieves state-of-the-art performance in reconstruction quality, efficiency, and robustness. The code is publicly available at: https://github.com/eezkni/Perceptual-GS
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。
