Mode-GS：面向鲁棒地面视角场景渲染的单目深度引导锚定3D高斯泼溅
Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering
AI总结：
针对地面机器人数据集渲染中高斯泼溅漂移问题，提出Mode-GS算法，结合单目深度锚点与残差解码器，通过尺度校准提升渲染质量，在多个数据集上达到SOTA。
摘要：
我们提出了一种面向地面机器人轨迹数据集的新视角渲染算法Mode-GS。该方法基于锚定高斯泼溅（anchored Gaussian splats），旨在克服现有3D高斯泼溅算法的局限性。此前的神经渲染方法因场景复杂度和多视角观测不足，存在严重的泼溅漂移问题，在地面机器人数据集中难以将泼溅固定在真实几何结构上。我们的方法整合了来自单目深度的像素对齐锚点，并通过残差形式的高斯解码器围绕这些锚点生成高斯泼溅。为解决单目深度固有的尺度模糊问题，我们为锚点参数化了逐视角深度尺度，并采用尺度一致的深度损失进行在线尺度校准。在自由轨迹模式的地面场景中，该方法在PSNR、SSIM和LPIPS指标上提升了渲染性能，且在R3LIVE里程计数据集和Tanks and Temples数据集上达到了当前最优的渲染性能。
英文摘要：
We present a novel-view rendering algorithm, Mode-GS, for ground-robot trajectory datasets. Our approach is based on using anchored Gaussian splats, which are designed to overcome the limitations of existing 3D Gaussian splatting algorithms. Prior neural rendering methods suffer from severe splat drift due to scene complexity and insufficient multi-view observation, and can fail to fix splats on the true geometry in ground-robot datasets. Our method integrates pixel-aligned anchors from monocular depths and generates Gaussian splats around these anchors using residual-form Gaussian decoders. To address the inherent scale ambiguity of monocular depth, we parameterize anchors with per-view depth-scales and employ scale-consistent depth loss for online scale calibration. Our method results in improved rendering performance, based on PSNR, SSIM, and LPIPS metrics, in ground scenes with free trajectory patterns, and achieves state-of-the-art rendering performance on the R3LIVE odometry dataset and the Tanks and Temples dataset.
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。
