LiDAR Point Cloud Processing

The latest 3D acquisition mechanisms have enabled the modelling of real 3D scenes using unordered sets of 3D points, which can be accompanied by different attributes, e.g., colour components, normals, semantic labels, and sensing-related measurements.

These sets of points are called Point Clouds and they are typically composed of hundreds of points; that is why they are always storage-consuming and always require a long time to be processed.

Among the most popular acquisition systems, we can find LiDARs. These devices use the light from a laser, producing a sparse prediction of the environment in the form of point clouds. LiDAR point clouds are common data used in various deep learning tasks such as visual scene understanding, compression and completion.

Read more here: https://medium.com/@elenacamuffo97/recent-advancements-in-learning-algorithms-for-point-clouds-an-updated-overview-35eabf511183

Key research topics include:

  • Point cloud semantic segmentation
  • Point cloud semantic compression

Recent publications:

Barbato, Francesco; Camuffo, Elena; Milani, Simone; Zanuttigh, Pietro

Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network Proceedings Article

In: IEEE International Conference on Image Processing (ICIP), 2024.

Abstract | Links | BibTeX

Devid, Campagnolo*; Elena, Camuffo*; Umberto, Michieli; Paolo, Borin; Simone, Milani; Andrea, Giordano

Fully Automated Scan-to-BIM via Point Cloud Instance Segmentation Proceedings Article

In: International Conference on Image Processing (ICIP), IEEE 2023.

Abstract | Links | BibTeX

Mari, Daniele; Camuffo, Elena; Milani, Simone

CACTUS: Content-Aware Compression and Transmission Using Semantics for Automotive LiDAR Data Journal Article

In: Sensors, vol. 23, iss. 12, 2023.

Abstract | Links | BibTeX

Camuffo, Elena; Milani, Simone

Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data Proceedings Article

In: International Conference of Computer Vision and Pattern Recognition Workshops, 2023.

Abstract | Links | BibTeX

Camuffo, Elena; Michieli, Umberto; Milani, Simone

Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation Journal Article

In: IEEE Transactions on Multimedia, pp. 1-11, 2023.

Abstract | Links | BibTeX

Camuffo, Elena; Mari, Daniele; Milani, Simone

Recent advancements in learning algorithms for point clouds: An updated overview Journal Article

In: Sensors, vol. 22, no. 4, pp. 1357, 2022.

Abstract | Links | BibTeX

Milani, Simone

Adae: Adversarial distributed source autoencoder for point cloud compression Proceedings Article

In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 3078–3082, IEEE 2021.

BibTeX

Agresti, Gianluca; Milani, Simone

Material identification using RF sensors and convolutional neural networks Proceedings Article

In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3662–3666, IEEE 2019.

BibTeX

Lecci, Mattia; Milani, Simone

3D reconstruction from web harvested images using a forensic quality metric Proceedings Article

In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1997–2001, IEEE 2017.

BibTeX