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 with fixed-resolution baselines, while maintaining on par results in terms of reconstruction accuracy, offering a practical and extensible solution for high-performance 3D reconstruction.

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 real-time robotics estimation tasks.

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.

The introduction of new key features into the core specification of Bluetooth Low Energy (BLE) increased its potentialities, thus paving the way to the development of new networking paradigms. The ability for a single node to participate in more than a piconet and to assume both the role of master and slave makes it possible the formation of multi-hop networks that can be used in several emerging application scenarios. Additionally, the inherent low power consumption at the cost of contained throughput makes this technology appealing for Internet of Things (IoT), where power memory and capacity constrained devices exchange messages at relatively low data rates. In this paper, we devise a two layers BLE mesh-based networking paradigm obtained by generalizing Android BE-MESH for hardware-independent sensor networks. Each node enforces a plug-and-play architecture which makes it able to autonomously switch between client and server role, discover and connect to existing scatternets and relay messages through them, making the network able to extend and self re-organize in a distributed fashion. To have our implementation ready for IoT systems we based it on the ESP32 off-the-shelf board. We describe both the implemented functions as well as some practical results proving the effectiveness of the framework in some tested configurations.