360-GS: 面向室内漫游的布局引导全景高斯泼溅
360-GS: Layout-guided Panoramic Gaussian Splatting For Indoor Roaming
AI总结：
针对3D-GS应用于稀疏全景输入时存在的球面投影建模难、无纹理平面漂浮伪影多等问题，提出结合切平面投影与布局先验的360-GS方法，提升了室内新视角合成质量，支持沉浸式漫游。
摘要：
3D高斯泼溅（3D-GS）凭借实时且照片级真实感的渲染能力近期受到广泛关注。该技术通常以透视图像为输入，优化一组三维椭圆高斯体，将其泼溅到图像平面上生成二维高斯分布。然而，将3D-GS应用于全景输入时，存在用二维高斯有效建模360°图像球面投影的难题。在实际应用中，输入全景图通常较为稀疏，会导致三维高斯初始化不可靠，进而降低3D-GS的重建质量。此外，由于无纹理平面（如墙面和地板）的几何约束不足，3D-GS难以用椭圆高斯体建模这些平坦区域，导致新视角中出现大量漂浮伪影。为解决这些问题，我们提出360-GS，一种适用于有限全景输入的新型360°高斯泼溅方法。360-GS并非将三维高斯直接泼溅到球面上，而是先将其投影到单位球的切平面，再映射为球面投影，这种适配使得用高斯表示投影成为可能。我们利用全景图中的布局先验引导360-GS的优化，这类先验易于获取且包含室内场景的强结构信息。实验结果表明，360-GS可实现全景渲染，在新视角合成任务中效果优于现有最优方法，伪影更少，可为室内场景提供沉浸式漫游体验。
英文摘要：
3D Gaussian Splatting (3D-GS) has recently attracted great attention with real-time and photo-realistic renderings. This technique typically takes perspective images as input and optimizes a set of 3D elliptical Gaussians by splatting them onto the image planes, resulting in 2D Gaussians. However, applying 3D-GS to panoramic inputs presents challenges in effectively modeling the projection onto the spherical surface of ${360^\circ}$ images using 2D Gaussians. In practical applications, input panoramas are often sparse, leading to unreliable initialization of 3D Gaussians and subsequent degradation of 3D-GS quality. In addition, due to the under-constrained geometry of texture-less planes (e.g., walls and floors), 3D-GS struggles to model these flat regions with elliptical Gaussians, resulting in significant floaters in novel views. To address these issues, we propose 360-GS, a novel $360^{\circ}$ Gaussian splatting for a limited set of panoramic inputs. Instead of splatting 3D Gaussians directly onto the spherical surface, 360-GS projects them onto the tangent plane of the unit sphere and then maps them to the spherical projections. This adaptation enables the representation of the projection using Gaussians. We guide the optimization of 360-GS by exploiting layout priors within panoramas, which are simple to obtain and contain strong structural information about the indoor scene. Our experimental results demonstrate that 360-GS allows panoramic rendering and outperforms state-of-the-art methods with fewer artifacts in novel view synthesis, thus providing immersive roaming in indoor scenarios.
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。
