面向实时高保真动态场景重建的超点高斯泼溅
Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction
AI总结：
本文提出超点高斯泼溅（SP-GS）框架，通过将具有相似属性的3D高斯聚类为超点，以极小的计算开销将高斯泼溅扩展到动态场景，实现高分辨率下的实时渲染与最先进视觉质量，并增强场景操控能力。
摘要：
在动态场景中渲染新视角图像是一项关键但具有挑战性的任务。当前方法主要利用基于NeRF的方法来表示静态场景，并使用额外的时间变化MLP来建模场景形变，导致渲染质量相对较低且推理速度较慢。为了解决这些挑战，我们提出了一种名为超点高斯泼溅（SP-GS）的新框架。具体而言，我们的框架首先采用显式3D高斯来重建场景，然后将具有相似属性（例如旋转、平移和位置）的高斯聚类为超点。借助这些超点，我们的方法能够将3D高斯泼溅扩展到动态场景，同时仅略微增加计算开销。除了在高分辨率下实现最先进的视觉质量和实时渲染外，超点表示还提供了更强的操控能力。大量实验证明了我们的方法在合成数据集和真实世界数据集上的实用性和有效性。请访问我们的项目页面：https://dnvtmf.github.io/SP_GS.github.io。
英文摘要：
Rendering novel view images in dynamic scenes is a crucial yet challenging task. Current methods mainly utilize NeRF-based methods to represent the static scene and an additional time-variant MLP to model scene deformations, resulting in relatively low rendering quality as well as slow inference speed. To tackle these challenges, we propose a novel framework named Superpoint Gaussian Splatting (SP-GS). Specifically, our framework first employs explicit 3D Gaussians to reconstruct the scene and then clusters Gaussians with similar properties (e.g., rotation, translation, and location) into superpoints. Empowered by these superpoints, our method manages to extend 3D Gaussian splatting to dynamic scenes with only a slight increase in computational expense. Apart from achieving state-of-the-art visual quality and real-time rendering under high resolutions, the superpoint representation provides a stronger manipulation capability. Extensive experiments demonstrate the practicality and effectiveness of our approach on both synthetic and real-world datasets. Please see our project page at https://dnvtmf.github.io/SP_GS.github.io.
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。
