Publications | Lorenzo De Rebotti

2025

Resolution Where It Counts: Hash-based GPU-Accelerated 3D Reconstruction via Variance-Adaptive Voxel Grids

Lorenzo De Rebotti, Emanuele Giacomini, Giorgio Grisetti, and 1 more author

ACM Trans. Graph., Nov 2025

Abs DOI HTML Code

Efficient and scalable 3D surface reconstruction from range data remains a core challenge in computer graphics and vision, particularly in real-time and resource-constrained scenarios. Traditional volumetric methods based on fixed-resolution voxel grids or hierarchical structures like octrees often suffer from memory inefficiency, computational overhead, and a lack of GPU support. We propose a novel variance-adaptive, multi-resolution voxel grid that dynamically adjusts voxel size based on the local variance of signed distance field (SDF) observations. Unlike prior multi-resolution approaches that rely on recursive octree structures, our method leverages a flat spatial hash table to store all voxel blocks, supporting constant-time access and full GPU parallelism. This design enables high memory efficiency, and real-time scalability. We further demonstrate how our representation supports GPU-accelerated rendering through a parallel quad-tree structure for Gaussian Splatting, enabling effective control over splat density. Our open-source CUDA/C++ implementation achieves up to 13× speedup and 4× lower memory usage compared to fixed-resolution baselines, while maintaining on par results in terms of reconstruction accuracy, offering a practical and extensible solution for high-performance 3D reconstruction.
Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping

Emanuele Giacomini, Luca Di Giammarino, Lorenzo De Rebotti, and 2 more authors

In Proceedings of the IEEE/CVF International Conference on Computer Vision, Nov 2025

Abs PDF Code

LiDARs provide accurate geometric measurements, making them valuable for ego-motion estimation and reconstruction tasks. Although its success, managing an accurate and lightweight representation of the environment still poses challenges. Both classic and NeRF-based solutions have to trade off accuracy over memory and processing times. In this work, we build on recent advancements in Gaussian Splatting methods to develop a novel LiDAR odometry and mapping pipeline that exclusively relies on Gaussian primitives for its scene representation. Leveraging spherical projection, we drive the refinement of the primitives uniquely from LiDAR measurements. Experiments show that our approach matches the current registration performance, while achieving SOTA results for mapping tasks with minimal GPU requirements. This efficiency makes it a strong candidate for further exploration and potential adoption in realtime robotics estimation tasks.

2024

Structureless Bundle Adjustment for Robotics

Lorenzo De Rebotti and Giorgio Grisetti

In Proceedings of the Italian Conference on Robotics and Intelligent Machines, Oct 2024

Abs DOI HTML PDF

Global Epipolar Adjustment is an alternative formulation for solving the Bundle Adjustment problem without explicitly considering the points in the map, hence it is structureless. Albeit computationally interesting, this formulation has not found extensive use in robotics applications. In this paper we experimentally analyze the advantages and the shortcomings of GEA and BA. The goal of this work is to characterize the situations when the use of one might be convenient over the other. We made available an open source C++ implementation of all approaches at the time of writing.
VBR: A Vision Benchmark in Rome

Leonardo Brizi, Emanuele Giacomini, Luca Di Giammarino, and 4 more authors

In 2024 IEEE International Conference on Robotics and Automation (ICRA), May 2024

Abs DOI Code Website

This paper presents a vision and perception research dataset collected in Rome, featuring RGB data, 3D point clouds, IMU, and GPS data. We introduce a new benchmark targeting visual odometry and SLAM, to advance the research in autonomous robotics and computer vision. This work complements existing datasets by simultaneously addressing several issues, such as environment diversity, motion patterns, and sensor frequency. It uses up-to-date devices and presents effective procedures to accurately calibrate the intrinsic and extrinsic of the sensors while addressing temporal synchronization. During recording, we cover multi-floor buildings, gardens, urban and highway scenarios. Combining handheld and car-based data collections, our setup can simulate any robot (quadrupeds, quadrotors, autonomous vehicles). The dataset includes an accurate 6-dof ground truth based on a novel methodology that refines the RTK-GPS estimate with LiDAR point clouds through Bundle Adjustment (BA). All sequences divided in training and testing are accessible at www.rvp-group.net/datasets/slam.