2DGS-Room：帶有幾何約束的種子引導2D高斯塗抹，用於高保真度室內場景重建

2DGS-Room: Seed-Guided 2D Gaussian Splatting with Geometric Constrains for High-Fidelity Indoor Scene Reconstruction

December 4, 2024

作者: Wanting Zhang, Haodong Xiang, Zhichao Liao, Xiansong Lai, Xinghui Li, Long Zeng

cs.AI

摘要

由於空間結構的固有複雜性和無紋理區域的普遍存在，室內場景的重建仍然具有挑戰性。最近在3D高斯擴散方面的進展改善了新視角合成的加速處理，但在表面重建方面尚未提供可比擬的性能。本文介紹了一種名為2DGS-Room的新方法，利用2D高斯擴散來實現高保真度的室內場景重建。具體來說，我們採用種子引導機制來控制2D高斯分佈，通過自適應生長和修剪機制動態優化種子點的密度。為了進一步提高幾何精度，我們結合單眼深度和法向先驗來分別為細節和無紋理區域提供約束。此外，採用多視角一致性約束來減輕藝術品並進一步增強重建質量。在ScanNet和ScanNet++數據集上進行的大量實驗表明，我們的方法在室內場景重建方面實現了最先進的性能。

English

The reconstruction of indoor scenes remains challenging due to the inherent complexity of spatial structures and the prevalence of textureless regions. Recent advancements in 3D Gaussian Splatting have improved novel view synthesis with accelerated processing but have yet to deliver comparable performance in surface reconstruction. In this paper, we introduce 2DGS-Room, a novel method leveraging 2D Gaussian Splatting for high-fidelity indoor scene reconstruction. Specifically, we employ a seed-guided mechanism to control the distribution of 2D Gaussians, with the density of seed points dynamically optimized through adaptive growth and pruning mechanisms. To further improve geometric accuracy, we incorporate monocular depth and normal priors to provide constraints for details and textureless regions respectively. Additionally, multi-view consistency constraints are employed to mitigate artifacts and further enhance reconstruction quality. Extensive experiments on ScanNet and ScanNet++ datasets demonstrate that our method achieves state-of-the-art performance in indoor scene reconstruction.