IAS-LAB PUBLICATIONS
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
Non assegn||AREA MIN. 09 – Ingegneria industriale e dell’informazione||AREA MIN. 09 – Ingegneria industriale e dell’informazione – 2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Authors: Non assegn; 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. 02 – Scienze fisiche||AREA MIN. 02 – Scienze fisiche||Non assegn||AREA MIN. 02 – Scienze fisiche||Non assegn||AREA MIN. 14 – Scienze politiche e sociali||Non assegn||Non assegn||Non assegn||Non assegn||Non assegn||AREA MIN. 02 – Scienze fisiche||AREA MIN. 02 – Scienze fisiche||AREA MIN. 01 – Scienze matematiche e informatiche||Non assegn||AREA MIN. 02 – Scienze fisiche||Non assegn||AREA MIN. 02 – Scienze fisiche||Non assegn||AREA MIN. 02 – Scienze fisiche||AREA MIN. 02 – Scienze fisiche||Non assegn||AREA MIN. 09 – Ingegneria industriale e dell’informazione||Non assegn||Non assegn||AREA MIN. 06 – Scienze mediche||Non assegn – EDP Sciences
Authors: AREA MIN. 02 - Scienze fisiche; Non assegn; AREA MIN. 14 - Scienze politiche e sociali; AREA MIN. 01 - Scienze matematiche e informatiche; AREA MIN. 09 - Ingegneria industriale e dell'informazione; AREA MIN. 06 - Scienze mediche
Non assegn||Non assegn||Non assegn||Non assegn||AREA MIN. 02 – Scienze fisiche||AREA MIN. 02 – Scienze fisiche||Non assegn||Non assegn||AREA MIN. 09 – Ingegneria industriale e dell’informazione||AREA MIN. 06 – Scienze mediche||AREA MIN. 02 – Scienze fisiche||Non assegn||AREA MIN. 02 – Scienze fisiche||Non assegn – publisher
Authors: Non assegn; AREA MIN. 02 - Scienze fisiche; AREA MIN. 09 - Ingegneria industriale e dell'informazione; AREA MIN. 06 - Scienze mediche
AREA MIN. 09 – Ingegneria industriale e dell’informazione
Authors: AREA MIN. 09 - Ingegneria industriale e dell'informazione
AREA MIN. 09 – Ingegneria industriale e dell’informazione – Workshop on Artificial Intelligence and Robotics (AIRO), International Conference of the Italian Association for Artificial Intelligence (AIXIA)
Authors: AREA MIN. 09 - Ingegneria industriale e dell'informazione
AREA MIN. 09 – Ingegneria industriale e dell’informazione||AREA MIN. 09 – Ingegneria industriale e dell’informazione – publisher
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