|
|
| Academic Year |
2023/2024 |
| Name |
Dott. - MI (1380) Ingegneria dell'Informazione / Information Technology |
| Programme Year |
1 |
| ID Code |
061636 |
| Course Title |
ADVANCED DEEP LEARNING MODELS AND METHODS FOR 3D SPATIAL DATA |
| Course Type |
MONO-DISCIPLINARY COURSE |
| Credits (CFU / ECTS) |
5.0 |
| Course Description |
The course aims at providing students with a solid understanding of Deep Learning models for solving 3D Computer Vision tasks.
Deep Learning for 3D Point Clouds and Meshes (Boracchi): The most popular and successful deep learning models are meant for data lying over a rigid grid. Fully connected and convolutional layers are designed to process scattered data, as Point Clouds or 3D meshes returned by 3D sensors that are nowadays ubiquitous. In this lecture we will provide a formal description of 3D point clouds and meshes, and illustrate the type of sensors where these originates from. Then, we will introduce the mainstream solutions for solving visual recognition problems on Point Clouds (e.g. PointNet), including point-convolutional layers that extend the popular 2D convolutional layers to these type of data (e.g. KPConv, ConvPoint). The most successful deep learning models for solving Point Cloud classification and semantic segmentation will be then presented.
Deep Learning for Depth Estimation (Magri):
Obtaining dense and accurate depth measurement from images is a fundamental task for many 3D computer vision applications. In the last few years, depth estimation has undergone a paradigm shift due to the introduction of learning-based methods that have successfully replaced heuristics and hand-crafted rules. In particular, we will introduce the most relevant solution to single-view depth estimation which is an inherently ill-posed problem, and becomes tractable thanks to learned prior on 3D scenes. Then, we will move to multi-view depth estimation networks that improves the results even in configurations that are challenging for traditional methods (wide baseline) and exploits geometric constraints in the regression of the depth.
Deep Learning in 3D Non-rigid Shape Registration (Melzi) A challenging problem in computational geometry is to estimate correspondences between two shapes representing two deformed versions of the same entity (e.g., a dog in two different poses) or two entities from the same class (e.g., two chairs). This task, known as shape registration, finds several applications including texture/deformation transfer and statistical shape analysis. Many solutions for shape registration arise from rigid counterparts, by extending mainstream solutions like iterative closest points (ICP), coherent point drift (CPD), and methods based on the definition of pointwise descriptors (SHOT, HKS, among others). In the last decade, the functional approach (Functional maps) has given rise to a vast family of efficient alternatives. More recently, the large availability of data-driven solutions paved the way for machine learning procedures that rapidly outperformed all axiomatic competitors. In this lecture, we will overview some of the most impactful shape registration pipelines focusing in particular on the ones that inspired recent data-driven solutions (pointwise signatures and functional maps). Furthermore, we will analyse how well-known machine learning architectures have been applied to the shape registration task (CNN and transformers).
Deep Learning in 3D for Robotics (Matteucci) leveraging on the background from the previous lectures applications of deep learning methods for 3D data processing in robotics and autonomous vehicles will be presented highlighting the challenges of interpreting the 3D semantics of the environments with the purpose of interacting with it. Examples of applications which will be presented concerns 3D object pose reconstruction for grasping, 3D object detection and tracking for monitoring (i.e., with static observer) and for obstacle avoidance (i.e., moving observer), 3D semantic scene parsing for autonomous driving, 3D loop detection in Simultaneous Localization and Mapping, etc. |
| Scientific-Disciplinary Sector (SSD)
|
--
|
|
Alphabetical group
|
Name
|
Teaching Assignment Details
|
|
From (included)
|
To (excluded)
|
|
A
|
ZZZZ
|
Boracchi Giacomo, Magri Luca, Matteucci Matteo, Melzi Simone
|
|
|
