无需深度标注，从多张图像重建3D平面结构并生成高质量渲染。
Planar Gaussian Splatting
- 用高斯点建模场景，通过层次化混合分组识别3D平面实例。
- 在无3D平面标签和深度监督下达到当前最优的3D平面重建性能。
- 适用于跨数据集场景，推理速度远超传统优化方法，适合实际应用。
本文提出一种新型神经渲染方法——平面高斯点积（Planar Gaussian Splatting, PGS），直接从多张RGB图像学习3D几何结构并解析3D平面。PGS利用高斯原语建模场景，并采用层次化高斯混合方法对它们进行分组。相似的高斯点在树状结构的高斯混合中逐步概率性合并，以识别独立的3D平面实例并构建整体3D场景几何。为支持分组，高斯原语包含额外参数，如由通用2D分割模型生成的2D掩码投影得到的平面描述符和表面法向量。实验表明，所提方法在无需3D平面标签或深度监督的情况下，实现了当前最优的3D平面重建性能。相比依赖标注的现有监督方法在域偏移下表现下降，PGS凭借其神经渲染与场景特定优化机制，在多个数据集上保持稳定性能，且显著快于现有基于优化的方法。
原文摘要 · Abstract (English)
This paper presents Planar Gaussian Splatting (PGS), a novel neural rendering approach to learn the 3D geometry and parse the 3D planes of a scene, directly from multiple RGB images. The PGS leverages Gaussian primitives to model the scene and employ a hierarchical Gaussian mixture approach to group them. Similar Gaussians are progressively merged probabilistically in the tree-structured Gaussian mixtures to identify distinct 3D plane instances and form the overall 3D scene geometry. In order to enable the grouping, the Gaussian primitives contain additional parameters, such as plane descriptors derived by lifting 2D masks from a general 2D segmentation model and surface normals. Experiments show that the proposed PGS achieves state-of-the-art performance in 3D planar reconstruction without requiring either 3D plane labels or depth supervision. In contrast to existing supervised methods that have limited generalizability and struggle under domain shift, PGS maintains its performance across datasets thanks to its neural rendering and scene-specific optimization mechanism, while also being significantly faster than existing optimization-based approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。