优化3D高斯泼溅以实现稀疏视点场景重建
Optimizing 3D Gaussian Splatting for Sparse Viewpoint Scene Reconstruction
AI总结：
针对3DGS在稀疏视点下易产生伪影和性能下降的问题，提出SVS-GS框架，通过高斯平滑滤波、DGPP损失与SDS损失提升重建质量，在多个数据集上验证了其有效性。
摘要：
3D高斯泼溅（3DGS）已成为一种有前景的3D场景表示方法，与神经辐射场（NeRF）相比，它降低了计算开销。然而，3DGS容易受到高频伪影的影响，并且在稀疏视点条件下表现出次优性能，从而限制了其在机器人和计算机视觉中的应用。为了解决这些局限性，我们提出了SVS-GS，这是一个用于稀疏视点场景重建的新型框架，该框架集成了3D高斯平滑滤波器以抑制伪影。此外，我们的方法结合了带有动态深度掩码的深度梯度轮廓先验（DGPP）损失来锐化边缘，以及带有分数蒸馏采样（SDS）损失的2D扩散来增强新视图合成中的几何一致性。在MipNeRF-360和SeaThru-NeRF数据集上的实验评估表明，SVS-GS显著改善了稀疏视点下的3D重建，为机器人和计算机视觉应用中的场景理解提供了一种稳健且高效的解决方案。
英文摘要：
3D Gaussian Splatting (3DGS) has emerged as a promising approach for 3D scene representation, offering a reduction in computational overhead compared to Neural Radiance Fields (NeRF). However, 3DGS is susceptible to high-frequency artifacts and demonstrates suboptimal performance under sparse viewpoint conditions, thereby limiting its applicability in robotics and computer vision. To address these limitations, we introduce SVS-GS, a novel framework for Sparse Viewpoint Scene reconstruction that integrates a 3D Gaussian smoothing filter to suppress artifacts. Furthermore, our approach incorporates a Depth Gradient Profile Prior (DGPP) loss with a dynamic depth mask to sharpen edges and 2D diffusion with Score Distillation Sampling (SDS) loss to enhance geometric consistency in novel view synthesis. Experimental evaluations on the MipNeRF-360 and SeaThru-NeRF datasets demonstrate that SVS-GS markedly improves 3D reconstruction from sparse viewpoints, offering a robust and efficient solution for scene understanding in robotics and computer vision applications.
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。
