Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
This work addresses the problem of balancing reconstruction quality and efficiency in 3D scene representation for computer vision and graphics applications, offering a domain-specific incremental improvement.
The paper tackles the challenge of adaptively optimizing Gaussian primitive distribution in 3D Gaussian Splatting for novel view synthesis, proposing Perceptual-GS to integrate perceptual sensitivity, which achieves state-of-the-art performance in reconstruction quality, efficiency, and robustness on multiple datasets.
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