混合2D/3D高斯表示，提升平坦表面的重建质量与精度。
3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
- 用约束平面2D高斯建模平坦区域，其余用自由形式3D高斯。
- 在ScanNet++和ScanNetv2上实现最优深度估计性能。
- 适合需要高质量室内场景重建的研究与应用。
基于辐射场和新视角合成的最新进展可从照片生成逼真的数字孪生。然而，现有方法在处理平坦、无纹理表面时表现不佳，导致重建结果不均且半透明，这是由于光度重建目标病态所致。表面重建方法虽能解决此问题，但牺牲了视觉质量。本文提出一种新型的2D/3D混合表示，联合优化用于建模平坦表面的受限平面（2D）高斯和用于场景其余部分的自由形式（3D）高斯。该端到端方法可动态检测并精炼平面区域，同时提升视觉保真度与几何精度。在ScanNet++和ScanNetv2数据集上实现了最先进的深度估计效果，并在无需依赖特定相机模型的前提下表现出色，有效生成高质量室内场景重建。
原文摘要 · Abstract (English)
Recent advances in radiance fields and novel view synthesis enable creation of realistic digital twins from photographs. However, current methods struggle with flat, texture-less surfaces, creating uneven and semi-transparent reconstructions, due to an ill-conditioned photometric reconstruction objective. Surface reconstruction methods solve this issue but sacrifice visual quality. We propose a novel hybrid 2D/3D representation that jointly optimizes constrained planar (2D) Gaussians for modeling flat surfaces and freeform (3D) Gaussians for the rest of the scene. Our end-to-end approach dynamically detects and refines planar regions, improving both visual fidelity and geometric accuracy. It achieves state-of-the-art depth estimation on ScanNet++ and ScanNetv2, and excels at mesh extraction without overfitting to a specific camera model, showing its effectiveness in producing high-quality reconstruction of indoor scenes.
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。