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.

翻译：常见室内场景的高保真三维重建对于VR与AR应用至关重要。3D高斯溅射作为一种新型可微分渲染技术，凭借高渲染速度与相对较短训练时间，在新视角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，该方法在室内数据集常见场景中的表现欠佳。本研究探索利用易于获取的几何线索来增强高斯溅射在具有挑战性、病态及弱纹理场景中的优化效果。我们通过融合深度与法向线索扩展了3D高斯溅射方法，以应对复杂室内数据集，并展示了高效网格提取技术。具体而言，我们通过深度信息正则化优化过程，强制邻近高斯分布的局部平滑性，并利用现成的单目网络实现与真实场景几何的更好对齐。基于彩色图像梯度，我们提出了一种自适应深度损失函数，该函数在多种基线方法上实现了深度估计与新视角合成效果的提升。我们提出的简洁而有效的正则化技术可直接从高斯表示中提取网格，从而获得物理精度更高的室内场景重建结果。