Scholarlink

<p>In recent years, 3D Gaussian Splatting(3DGS) has attracted attention due to its ability to perform camera-level novel view synthesis(NVS) and 3D reconstruction through camera images with certain poses. Early works usually assumed that the input were good camera poses and RGB images, but the input obtained in actual robotics work is generally an erroneous pose and RGB-D image, which will have a serious impact on the geometry of scene reconstruction and NVS’s quality and waste depth information. In this paper, we propose a new scene reconstruction method based on RGB-D view synthesis and camera pose optimization, which is robust to inaccurate pose estimation and incomplete views. This method optimizes the scene geometry, new views, and poses, and jointly learns the parameters of the Gaussians to obtain a 3D scene with accurate geometry and high quality of NVS, which has a 19.86% improvement on NVS quality and 23.73% improvement on depth estimation compared to the base method.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Robust Geometric Reconstruction of RGB-D Data Based on Gaussian Splatting

  • 期刊论文

  • 发表日期：

    2025年11月28日

查看全文
  • Yibin Zhao,
  • Jianjun Yi,
  • Yihan Pan,
  • Liwei Chen

摘要

In recent years, 3D Gaussian Splatting(3DGS) has attracted attention due to its ability to perform camera-level novel view synthesis(NVS) and 3D reconstruction through camera images with certain poses. Early works usually assumed that the input were good camera poses and RGB images, but the input obtained in actual robotics work is generally an erroneous pose and RGB-D image, which will have a serious impact on the geometry of scene reconstruction and NVS’s quality and waste depth information. In this paper, we propose a new scene reconstruction method based on RGB-D view synthesis and camera pose optimization, which is robust to inaccurate pose estimation and incomplete views. This method optimizes the scene geometry, new views, and poses, and jointly learns the parameters of the Gaussians to obtain a 3D scene with accurate geometry and high quality of NVS, which has a 19.86% improvement on NVS quality and 23.73% improvement on depth estimation compared to the base method.