Adaptive Plane Splatting for 3D Building Reconstruction

Abstract

In the last three years, 3DGS has attracted widespread attention due to its fast training and high-quality rendering, leading to numerous surface reconstruction studies proposing geometric constraints to extract high-quality meshes. Although these methods demonstrate potential for building model reconstruction, modern 3D building applications increasingly require watertight, Boundary Representation (B-rep) models for analytical tasks rather than the standard triangular meshes typically generated. On the other hand, traditional piecewise-planar reconstruction methods that rely on point clouds are often computationally heavy and unstable when generating plane hypotheses from noisy data. To address these limitations, this thesis proposes AdaptivePS, an adaptive, image-to-plane splatting pipeline for multi-view indoor and outdoor scene surface reconstruction. Designed to function as the foundational step in a broader "image to watertight building model" pipeline, it outputs planar primitives ready to be plugged into a piecewise-planar reconstructor. AdaptivePS extends the baseline PlanarSplatting method to outdoor environments by introducing a foreground mask generator and a novel prior generator that jointly recovers camera poses, depth, and normal maps in a single inference—bypassing SfM entirely while normalizing scenes to a consistent scale. Additionally, the pipeline employs a mask-guided densification and pruning strategy to adaptively split primitives at object boundaries and remove background noise, alongside a mask-guided trimming mechanism applied to sampled points for sharper boundary delineation. Experiments demonstrate that AdaptivePS achieves sufficient geometric quality for outdoor scenes while running 2x as fast as the baseline framework.

The code is available at https://github.com/MCHU-1999/AdaptivePS.