SplatMAP: 基于3D高斯溅射的在线稠密单目SLAM
SplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting
AI总结：
针对单目视频3D重建的精度与实时性难题，提出SplatMAP框架，将稠密SLAM与3D高斯溅射集成，通过SLAM感知自适应致密化和几何引导优化，实现实时高保真重建，在公开数据集上指标显著优于现有方法。
摘要：
由于结构光运动（SfM）和单目SLAM等传统方法在精确捕捉场景细节方面存在固有局限性，从单目视频实现高保真3D重建仍具挑战。虽然神经辐射场（NeRF）等可微分渲染技术解决了部分挑战，但其高计算成本使其不适合实时应用。此外，现有3D高斯溅射（3DGS）方法常聚焦光度一致性，忽视几何精度，且未利用SLAM的动态深度和位姿更新进行场景优化。我们提出一种将稠密SLAM与3DGS集成的框架，用于实时高保真稠密重建。该方法引入SLAM感知自适应致密化，通过利用SLAM的稠密点云动态更新和致密化高斯模型；还融入几何引导优化，结合边缘感知几何约束和光度一致性，联合优化3DGS场景表示的外观与几何，实现详细且精确的SLAM建图重建。在Replica和TUM-RGBD数据集上的实验证明了方法的有效性，在单目系统中达到最先进结果：Replica上PSNR为36.864、SSIM为0.985、LPIPS为0.040，较之前最优分别提升10.7%、6.4%、49.4%；TUM-RGBD上相同指标较最接近基线提升10.2%、6.6%、34.7%。这些结果凸显了该框架在弥合光度与几何稠密3D场景表示差距、为实用高效单目稠密重建铺路的潜力。
英文摘要：
Achieving high-fidelity 3D reconstruction from monocular video remains challenging due to the inherent limitations of traditional methods like Structure-from-Motion (SfM) and monocular SLAM in accurately capturing scene details. While differentiable rendering techniques such as Neural Radiance Fields (NeRF) address some of these challenges, their high computational costs make them unsuitable for real-time applications. Additionally, existing 3D Gaussian Splatting (3DGS) methods often focus on photometric consistency, neglecting geometric accuracy and failing to exploit SLAM's dynamic depth and pose updates for scene refinement. We propose a framework integrating dense SLAM with 3DGS for real-time, high-fidelity dense reconstruction. Our approach introduces SLAM-Informed Adaptive Densification, which dynamically updates and densifies the Gaussian model by leveraging dense point clouds from SLAM. Additionally, we incorporate Geometry-Guided Optimization, which combines edge-aware geometric constraints and photometric consistency to jointly optimize the appearance and geometry of the 3DGS scene representation, enabling detailed and accurate SLAM mapping reconstruction. Experiments on the Replica and TUM-RGBD datasets demonstrate the effectiveness of our approach, achieving state-of-the-art results among monocular systems. Specifically, our method achieves a PSNR of 36.864, SSIM of 0.985, and LPIPS of 0.040 on Replica, representing improvements of 10.7%, 6.4%, and 49.4%, respectively, over the previous SOTA. On TUM-RGBD, our method outperforms the closest baseline by 10.2%, 6.6%, and 34.7% in the same metrics. These results highlight the potential of our framework in bridging the gap between photometric and geometric dense 3D scene representations, paving the way for practical and efficient monocular dense reconstruction.
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。
