IAS-LAB PUBLICATIONS

Clear

Dynamic Agile Production Robots That Learn and Optimise Knowledge and Operations

Authors: corda__h2020::894c505a83ec064b4c5692e9e21305a7::corda__h2020::894c505a83ec064b4c5692e9e21305a7::600; AREA MIN. 09 - Ingegneria industriale e dell'informazione

Revisiting Retentive Networks for Fast Range-View 3D LiDAR Semantic Segmentation

Authors: Mosco Simone; Fusaro Daniel; Li Wanmeng; Pretto Alberto

Journal: 21101448752

Published: 2026

DOI: 10.1109/WACV61042.2026.00246

LiDAR semantic segmentation is a crucial task in autonomous driving and robotics, where real-time performance is essential for online decision-making. Recent trends exploit range images and Vision Transformers, using the self-attention mechanism. However, these approaches often lack explicit spatial priors and involve a large number of parameters. To tackle these limitations, we propose a novel method, adapting the Retentive Network architecture from the Natural Language Processing (NLP) field, for its efficient sequence modeling capabilities, directly operating on the range-view representation. Our approach incorporates a circular retention (CiR) mechanism that explicitly captures spatial relationships and continual circular property of the range image while modeling long-range dependencies and preserving the receptive field. In addition, we introduce a new set of range-view augmentations, adapted from 3D techniques, to improve generalization and mitigate class imbalance. Extensive experiments on three large-scale datasets, as SemanticKITTI, PandaSet and Semantic-POSS demonstrate that our method achieve state-of-the-art performance among range-view approaches on two out of three datasets, while satisfying real-time constraints. The code is available at https://github.com/SiMoM0/RangeRet.

Pages: 2499-2509

Keywords: 3d semantic segmentation; 3d vision; autonomous driving; retentive networks;

Point-plane projections for accurate LiDAR semantic segmentation in small data scenarios

Authors: Mosco Simone; Fusaro Daniel; Li Wanmeng; Menegatti Emanuele; Pretto Alberto

Journal: 24161

Published: 2026

DOI: 10.1016/j.cviu.2026.104902

LiDAR point cloud semantic segmentation is essential for interpreting 3D environments in applications such as autonomous driving and robotics. Recent methods achieve strong performance by exploiting different point cloud representations or incorporating data from other sensors, such as cameras or external datasets. However, these approaches often suffer from high computational complexity and require large amounts of training data, limiting their generalization in data-scarce scenarios. In this paper, we improve the performance of point-based methods by effectively learning features from 2D representations through point–plane projections, enabling the extraction of complementary information while relying solely on LiDAR data. Additionally, we introduce a geometry-aware technique for data augmentation that aligns with LiDAR sensor properties and mitigates class imbalance. We implemented and evaluated our method that applies point–plane projections onto multiple informative 2D representations of the point cloud. Experiments demonstrate that this approach leads to significant improvements in limited-data scenarios, while also achieving competitive results on three publicly available standard datasets, as SemanticKITTI, PandaSet and BikeScenes. The code of our method is available at https://github.com/SiMoM0/3PNet .

Volume: 271

Keywords: 3D semantic segmentation; Autonomous driving; LiDAR; Small data;

AREA MIN. 09 – Ingegneria industriale e dell’informazione

Authors: AREA MIN. 09 - Ingegneria industriale e dell'informazione

AREA MIN. 13 – Scienze economiche e statistiche – John Wiley and Sons Inc

Authors: AREA MIN. 13 - Scienze economiche e statistiche

DOI: 10.1002/clt2.70147