DrawSplat: Atlanta World-Guided Implicit Gaussian SLAM for Indoor Reconstruction
DrawSplat: Atlanta World-Guided Implicit Gaussian SLAM for Indoor Reconstruction
This research paper presents DrawSplat, a new Simultaneous Localization and Mapping (SLAM) system designed for indoor environments. By leveraging an Atlanta World prior to infer structural planes from tracked lines, the framework improves geometric consistency in scenes with weak textures and noisy depth data. Experiments demonstrate that DrawSplat outperforms existing Gaussian-based SLAM systems in tracking stability, rendering quality, and geometric accuracy while maintaining computational efficiency.
The paper introduces DrawSplat, a novel SLAM framework that integrates explicit point-line geometry with implicit neural Gaussians guided by an Atlanta World prior to address challenges in indoor reconstruction such as weak textures and noisy depth.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
Source：arXiv Robotics — research abstracts · arxiv.org