Blurred LiDAR for Sharper 3D: Robust Handheld 3D Scanning with Diffuse LiDAR and RGB

TL;DR

This paper introduces a novel diffuse LiDAR technique combined with RGB data to enhance 3D surface reconstruction, especially in challenging environments, outperforming traditional sparse LiDAR methods.

Contribution

The work proposes using diffuse LiDAR with a Gaussian surfel rendering framework and adaptive loss to improve scene coverage and accuracy in 3D scanning.

Findings

Diffuse LiDAR improves scene coverage over traditional sparse LiDAR.

The combined RGB and diffuse LiDAR approach yields more accurate geometry and color.

Diffuse LiDAR can outperform traditional sparse LiDAR in challenging environments.

Abstract

3D surface reconstruction is essential across applications of virtual reality, robotics, and mobile scanning. However, RGB-based reconstruction often fails in low-texture, low-light, and low-albedo scenes. Handheld LiDARs, now common on mobile devices, aim to address these challenges by capturing depth information from time-of-flight measurements of a coarse grid of projected dots. Yet, these sparse LiDARs struggle with scene coverage on limited input views, leaving large gaps in depth information. In this work, we propose using an alternative class of "blurred" LiDAR that emits a diffuse flash, greatly improving scene coverage but introducing spatial ambiguity from mixed time-of-flight measurements across a wide field of view. To handle these ambiguities, we propose leveraging the complementary strengths of diffuse LiDAR with RGB. We introduce a Gaussian surfel-based rendering framework with a scene-adaptive loss function that dynamically balances RGB and diffuse LiDAR signals. We demonstrate that, surprisingly, diffuse LiDAR can outperform traditional sparse LiDAR, enabling robust 3D scanning with accurate color and geometry estimation in challenging environments.