SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting

TL;DR

SurfFill is a novel method that combines LiDAR and camera data using Gaussian surfels to effectively complete large-scale 3D point clouds, especially in featureless or thin structures, outperforming previous methods.

Contribution

The paper introduces a Gaussian surfel-based LiDAR completion scheme that leverages ambiguity heuristics and a divide-and-conquer approach for large-scale scene reconstruction.

Findings

Outperforms previous reconstruction methods on synthetic and real-world data.

Effectively completes large-scale point clouds with improved accuracy.

Addresses artifacts caused by LiDAR beam divergence in thin structures.

Abstract

LiDAR-captured point clouds are often considered the gold standard in active 3D reconstruction. While their accuracy is exceptional in flat regions, the capturing is susceptible to miss small geometric structures and may fail with dark, absorbent materials. Alternatively, capturing multiple photos of the scene and applying 3D photogrammetry can infer these details as they often represent feature-rich regions. However, the accuracy of LiDAR for featureless regions is rarely reached. Therefore, we suggest combining the strengths of LiDAR and camera-based capture by introducing SurfFill: a Gaussian surfel-based LiDAR completion scheme. We analyze LiDAR capturings and attribute LiDAR beam divergence as a main factor for artifacts, manifesting mostly at thin structures and edges. We use this insight to introduce an ambiguity heuristic for completed scans by evaluating the change in density in the point cloud. This allows us to identify points close to missed areas, which we can then use to grow additional points from to complete the scan. For this point growing, we constrain Gaussian surfel reconstruction [Huang et al. 2024] to focus optimization and densification on these ambiguous areas. Finally, Gaussian primitives of the reconstruction in ambiguous areas are extracted and sampled for points to complete the point cloud. To address the challenges of large-scale reconstruction, we extend this pipeline with a divide-and-conquer scheme for building-sized point cloud completion. We evaluate on the task of LiDAR point cloud completion of synthetic and real-world scenes and find that our method outperforms previous reconstruction methods.