Publications by Roberto Vezzani

In recent years, Human Pose Estimation has achieved impressive results on RGB images. The advent of deep learning architectures and large annotated datasets have contributed to these achievements. However, little has been done towards estimating the human pose using depth maps, and especially towards obtaining a precise 3D body joint localization. To fill this gap, this paper presents RefiNet, a depth-based 3D human pose refinement framework. Given a depth map and an initial coarse 2D human pose, RefiNet regresses a fine 3D pose. The framework is composed of three modules, based on different data representations, i.e. 2D depth patches, 3D human skeletons, and point clouds. An extensive experimental evaluation is carried out to investigate the impact of the model hyper-parameters and to compare RefiNet with off-the-shelf 2D methods and literature approaches. Results confirm the effectiveness of the proposed framework and its limited computational requirements.

For decades, researchers of different areas, ranging from artificial intelligence to computer vision, have intensively investigated human-centered data, i.e., data in which the human plays a significant role, acquired through a non-invasive approach, such as cameras. This interest has been largely supported by the highly informative nature of this kind of data, which provides a variety of information with which it is possible to understand many aspects including, for instance, the human body or the outward appearance. Some of the main tasks related to human analysis are focused on the body (e.g., human pose estimation and anthropocentric measurement estimation), the hands (e.g., gesture detection and recognition), the head (e.g., head pose estimation), or the face (e.g., emotion and expression recognition). Additional tasks are based on non-corporal elements, such as motion (e.g., action recognition and human behavior understanding) and clothes (e.g., garment-based virtual try-on and attribute recognition). Unfortunately, privacy issues severely limit the usage and the diffusion of this kind of data, making the exploitation of learning approaches challenging. In particular, privacy issues behind the acquisition and the use of human-centered data must be addressed by public and private institutions and companies. Thirteen high-quality papers have been published in this Special Issue and are summarized in the following: four of them are focused on the human face (facial geometry, facial landmark detection, and emotion recognition), two on eye image analysis (eye status classification and 3D gaze estimation), five on the body (pose estimation, conversational gesture analysis, and action recognition), and two on the outward appearance (transferring clothing styles and fashion-oriented image captioning). These numbers confirm the high interest in human-centered data and, in particular, the variety of real-world applications that it is possible to develop.

Neural Radiance Fields (NeRFs) have gained widespread recognition as a highly effective technique for representing 3D reconstructions of objects and scenes derived from sets of images. Despite their efficiency, NeRF models can pose challenges in certain scenarios such as vehicle inspection, where the lack of sufficient data or the presence of challenging elements (e.g. reflections) strongly impact the accuracy of the reconstruction. To this aim, we introduce CarPatch, a novel synthetic benchmark of vehicles. In addition to a set of images annotated with their intrinsic and extrinsic camera parameters, the corresponding depth maps and semantic segmentation masks have been generated for each view. Global and part-based metrics have been defined and used to evaluate, compare, and better characterize some state-of-the-art techniques. The dataset is publicly released at https://aimagelab.ing.unimore.it/go/ carpatch and can be used as an evaluation guide and as a baseline for future work on this challenging topic.

The effective and reliable detection and classification of dynamic hand gestures is a key element for building Natural User Interfaces, systems that allow the users to interact using free movements of their body instead of traditional mechanical tools. However, methods that temporally segment and classify dynamic gestures usually rely on a great amount of labeled data, including annotations regarding the class and the temporal segmentation of each gesture. In this paper, we propose an unsupervised approach to train a Transformer-based architecture that learns to detect dynamic hand gestures in a continuous temporal sequence. The input data is represented by the 3D position of the hand joints, along with their speed and acceleration, collected through a Leap Motion device. Experimental results show a promising accuracy on both the detection and the classification task and that only limited computational power is required, confirming that the proposed method can be applied in real-world applications.

Knowing the exact 3D location of workers and robots in a collaborative environment enables several real applications, such as the detection of unsafe situations or the study of mutual interactions for statistical and social purposes. In this paper, we propose a non-invasive and light-invariant framework based on depth devices and deep neural networks to estimate the 3D pose of robots from an external camera. The method can be applied to any robot without requiring hardware access to the internal states. We introduce a novel representation of the predicted pose, namely Semi-Perspective Decoupled Heatmaps (SPDH), to accurately compute 3D joint locations in world coordinates adapting efficient deep networks designed for the 2D Human Pose Estimation. The proposed approach, which takes as input a depth representation based on XYZ coordinates, can be trained on synthetic depth data and applied to real-world settings without the need for domain adaptation techniques. To this end, we present the SimBa dataset, based on both synthetic and real depth images, and use it for the experimental evaluation. Results show that the proposed approach, made of a specific depth map representation and the SPDH, overcomes the current state of the art.

Recently, learning frameworks have shown the capability of inferring the accurate shape, pose, and texture of an object from a single RGB image. However, current methods are trained on image collections of a single category in order to exploit specific priors, and they often make use of category-specific 3D templates. In this paper, we present an alternative approach that infers the textured mesh of objects combining a series of deformable 3D models and a set of instance-specific deformation, pose, and texture. Differently from previous works, our method is trained with images of multiple object categories using only foreground masks and rough camera poses as supervision. Without specific 3D templates, the framework learns category-level models which are deformed to recover the 3D shape of the depicted object. The instance-specific deformations are predicted independently for each vertex of the learned 3D mesh, enabling the dynamic subdivision of the mesh during the training process. Experiments show that the proposed framework can distinguish between different object categories and learn category-specific shape priors in an unsupervised manner. Predicted shapes are smooth and can leverage from multiple steps of subdivision during the training process, obtaining comparable or state-of-the-art results on two public datasets. Models and code are publicly released.

Human Pose Estimation is a fundamental task for many applications in the Computer Vision community and it has been widely investigated in the 2D domain, i.e. intensity images. Therefore, most of the available methods for this task are mainly based on 2D Convolutional Neural Networks and huge manually-annotated RGB datasets, achieving stunning results. In this paper, we propose RefiNet, a multi-stage framework that regresses an extremely-precise 3D human pose estimation from a given 2D pose and a depth map. The framework consists of three different modules, each one specialized in a particular refinement and data representation, i.e. depth patches, 3D skeleton and point clouds. Moreover, we present a new dataset, called Baracca, acquired with RGB, depth and thermal cameras and specifically created for the automotive context. Experimental results confirm the quality of the refinement procedure that largely improves the human pose estimations of off-the-shelf 2D methods.

Event cameras are biologically-inspired sensors that gather the temporal evolution of the scene. They capture pixel-wise brightness variations and output a corresponding stream of asynchronous events. Despite having multiple advantages with respect to conventional cameras, their use is limited due to the scarce compatibility of asynchronous event streams with traditional data processing and vision algorithms. In this regard, we present a framework that synthesizes RGB frames from the output stream of an event camera and an initial or a periodic set of color key-frames. The deep learning-based frame synthesis framework consists of an adversarial image-to-image architecture and a recurrent module. Two public event-based datasets, DDD17 and MVSEC, are used to obtain qualitative and quantitative per-pixel and perceptual results. In addition, we converted into event frames two additional wellknown datasets, namely Kitti and Cityscapes, in order to present semantic results, in terms of object detection and semantic segmentation accuracy. Extensive experimental evaluation confirm the quality and the capability of the proposed approach of synthesizing frame sequences from color key-frames and sequences of intermediate events.

In this paper, we present a novel multi-task framework which aims to improve the performance of car model classification leveraging visual features and pose information extracted from single RGB images. In particular, we merge the visual features obtained through an image classification network and the features computed by a model able to predict the pose in terms of 2D car keypoints. We show how this approach considerably improves the performance on the model classification task testing our framework on a subset of the Pascal3D dataset containing the car classes. Finally, we conduct an ablation study to demonstrate the performance improvement obtained with respect to a single visual classifier network.