RGS：通过学习几何连续性实现反射物体的反射感知高斯泼溅
RGS: Reflection-aware Gaussian Splatting via Learning Geometry Continuity for Reflective Objects
浏览论文内容
中文总结 AI 辅助
针对三维高斯泼溅在反射区域表面塌陷问题，提出反射感知高斯泼溅（RGS），利用三维基础模型先验与跨视角正则化及反射感知稠密化，实现高质量镜面渲染与新视角合成。
中文摘要 AI 辅助
高斯泼溅通过显式高斯表示显著提升了新视角合成的质量。然而，我们观察到现有的三维高斯泼溅方法（3DGS）在反射区域常常面临表面塌陷问题，从而产生较差的几何形状和低质量的镜面反射效果。在这项工作中，我们提出了一种基于物理的延迟渲染框架，名为反射感知高斯泼溅（RGS），能够精确建模镜面区域并提升新视角合成性能。具体而言，我们发现一个强大的三维基础模型可以提供强有力的三维几何先验，以促进正确的几何建模。基于此，我们提出了一种跨视角形状一致性正则化方法，利用大型模型先验和跨视角约束来规范几何表面。通过这种方式，我们的RGS能够在反射区域生成更平滑的几何表面，同时减少几何空洞。为了进一步改善反射区域的渲染结果，我们提出了一种反射感知的稠密化策略，旨在捕捉不同视角下的镜面变化。借助这一策略，我们的RGS能够以更高质量渲染物体的新视角。大量实验表明，我们的方法能够持续渲染高质量的反射物体，达到了最先进的性能。
英文摘要
Gaussian Splatting has significantly improved the quality of novel view synthesis with explicit Gaussian representation. However, we observed that existing 3D Gaussian Splatting methods (3DGS) often suffer from surface collapse issues on reflective regions, and thus produce inferior geometry and low-quality specular. In this work, we propose a physically-based deferred rendering framework, named Reflection-aware Gaussian Splatting (RGS), that can accurately model specular regions and improve novel view synthesis performance. Specifically, we found that a powerful 3D foundation model can provide a strong 3D geometric prior to foster correct geometric modeling. Based on this, we propose a cross-view shape consistency regularization to regularize the geometry surface with the large model prior and cross-view constraints. In this manner, our RGS can produce smoother geometric surfaces on reflective regions while reducing geometric hollows. To further improve rendering results on reflective regions, we present a reflection-aware densification strategy that is designed to capture specular variations across various views. With this strategy, our RGS is able to render novel views of objects in higher quality. Extensive experiments demonstrate our method consistently renders high-quality reflective objects, achieving state-of-the-art performance.
发表机构
- University of Technology Sydney（悉尼科技大学）
- Adelaide University（阿德莱德大学）
- Li Auto Inc.（理想汽车）
机构由 AI 辅助整理，请以论文原文为准。
