DN-Splatter：用于高斯泼溅与网格化的深度与法线先验
DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing
AI总结：
针对室内场景三维重建，提出利用深度与法线先验正则化高斯泼溅优化，并引入自适应深度损失，实现高效网格提取与更精确的重建。
摘要：
高保真度的常见室内场景三维重建对于VR和AR应用至关重要。三维高斯泼溅作为一种新颖的可微渲染技术，在实现高渲染速度和相对较短训练时间的同时，已在新视图合成任务中取得了最先进的成果。然而，由于优化过程中缺乏几何约束，该技术在室内数据集中常见场景上的表现较差。在本工作中，我们探索利用易于获取的几何线索来增强高斯泼溅在具有挑战性、病态且无纹理场景中的优化。我们通过深度和法线线索扩展三维高斯泼溅，以应对具有挑战性的室内数据集，并展示了高效的网格提取技术。具体而言，我们利用深度信息对优化过程进行正则化，强制邻近高斯体的局部平滑性，并使用现成的单目网络以更好地对齐真实场景几何。我们提出了一种基于彩色图像梯度的自适应深度损失，从而在多种基线上改善了深度估计和新视图合成结果。我们简单而有效的正则化技术使得能够直接从高斯表示中提取网格，从而生成更物理精确的室内场景重建。
英文摘要：
High-fidelity 3D reconstruction of common indoor scenes is crucial for VR and AR applications. 3D Gaussian splatting, a novel differentiable rendering technique, has achieved state-of-the-art novel view synthesis results with high rendering speeds and relatively low training times. However, its performance on scenes commonly seen in indoor datasets is poor due to the lack of geometric constraints during optimization. In this work, we explore the use of readily accessible geometric cues to enhance Gaussian splatting optimization in challenging, ill-posed, and textureless scenes. We extend 3D Gaussian splatting with depth and normal cues to tackle challenging indoor datasets and showcase techniques for efficient mesh extraction. Specifically, we regularize the optimization procedure with depth information, enforce local smoothness of nearby Gaussians, and use off-the-shelf monocular networks to achieve better alignment with the true scene geometry. We propose an adaptive depth loss based on the gradient of color images, improving depth estimation and novel view synthesis results over various baselines. Our simple yet effective regularization technique enables direct mesh extraction from the Gaussian representation, yielding more physically accurate reconstructions of indoor scenes.
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。
