MVGSR：用于鲁棒表面重建的多视图一致性高斯泼溅
MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstruction
AI总结：
针对3DGS在含动态物体与干扰物场景中表面重建出现漂浮伪影和颜色误差的问题，提出MVGSR，通过多视图特征一致性掩蔽干扰物、贡献剪枝重置透射率及一致性损失，提升几何精度与渲染保真度。
摘要：
3D Gaussian Splatting（3DGS，三维高斯泼溅）因其高质量渲染能力、超快训练和推理速度而受到广泛关注。然而，当我们将3DGS应用于表面重建任务时，尤其是在存在动态物体和干扰物的环境中，由于不同视点之间的不一致性，该方法会出现漂浮伪影和颜色误差。为应对这一挑战，我们提出面向鲁棒表面重建领域的多视图一致性高斯泼溅（MVGSR），它利用轻量级高斯模型和启发式引导的干扰物掩蔽策略，在非静态环境中实现鲁棒表面重建。与现有依赖MLP进行干扰物分割的方法相比，我们的方法通过比较多视图特征一致性，将干扰物与静态场景元素分离，从而能够在训练早期获得精确的干扰物掩膜。此外，我们引入了一种基于多视图贡献的剪枝度量来重置透射率，有效减少漂浮伪影。最后，采用多视图一致性损失以在表面重建任务中实现高质量性能。实验结果表明，与最先进的表面重建算法相比，MVGSR取得了具有竞争力的几何精度和渲染保真度。更多信息可在项目页面（https://mvgsr.github.io）获取。
英文摘要：
3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to surface reconstruction tasks, especially in environments with dynamic objects and distractors, the method suffers from floating artifacts and color errors due to inconsistency from different viewpoints. To address this challenge, we propose Multi-View Consistency Gaussian Splatting for the domain of Robust Surface Reconstruction (\textbf{MVGSR}), which takes advantage of lightweight Gaussian models and a {heuristics-guided distractor masking} strategy for robust surface reconstruction in non-static environments. Compared to existing methods that rely on MLPs for distractor segmentation strategies, our approach separates distractors from static scene elements by comparing multi-view feature consistency, allowing us to obtain precise distractor masks early in training. Furthermore, we introduce a pruning measure based on multi-view contributions to reset transmittance, effectively reducing floating artifacts. Finally, a multi-view consistency loss is applied to achieve high-quality performance in surface reconstruction tasks. Experimental results demonstrate that MVGSR achieves competitive geometric accuracy and rendering fidelity compared to the state-of-the-art surface reconstruction algorithms. More information is available on our project page (https://mvgsr.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。
