Roberto Vezzani

Davide Di Nucci, Alessandro Simoni, Matteo Tomei et al.

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.

Alessandro Simoni, Stefano Pini, Guido Borghi et al.

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.

Davide Di Nucci, Alessandro Simoni, Matteo Tomei et al.

The three-dimensional representation of objects or scenes starting from a set of images has been a widely discussed topic for years and has gained additional attention after the diffusion of NeRF-based approaches. However, an underestimated prerequisite is the knowledge of camera poses or, more specifically, the estimation of the extrinsic calibration parameters. Although excellent general-purpose Structure-from-Motion methods are available as a pre-processing step, their computational load is high and they require a lot of frames to guarantee sufficient overlapping among the views. This paper introduces KRONC, a novel approach aimed at inferring view poses by leveraging prior knowledge about the object to reconstruct and its representation through semantic keypoints. With a focus on vehicle scenes, KRONC is able to estimate the position of the views as a solution to a light optimization problem targeting the convergence of keypoints' back-projections to a singular point. To validate the method, a specific dataset of real-world car scenes has been collected. Experiments confirm KRONC's ability to generate excellent estimates of camera poses starting from very coarse initialization. Results are comparable with Structure-from-Motion methods with huge savings in computation. Code and data will be made publicly available.

Alessandro Simoni, Francesco Marchetti, Guido Borghi et al.

Technologies to enable safe and effective collaboration and coexistence between humans and robots have gained significant importance in the last few years. A critical component useful for realizing this collaborative paradigm is the understanding of human and robot 3D poses using non-invasive systems. Therefore, in this paper, we propose a novel vision-based system leveraging depth data to accurately establish the 3D locations of skeleton joints. Specifically, we introduce the concept of Pose Nowcasting, denoting the capability of the proposed system to enhance its current pose estimation accuracy by jointly learning to forecast future poses. The experimental evaluation is conducted on two different datasets, providing accurate and real-time performance and confirming the validity of the proposed method on both the robotic and human scenarios.

Alessandro Simoni, Francesco Marchetti, Guido Borghi et al.

Despite the recent advances in computer vision research, estimating the 3D human pose from single RGB images remains a challenging task, as multiple 3D poses can correspond to the same 2D projection on the image. In this context, depth data could help to disambiguate the 2D information by providing additional constraints about the distance between objects in the scene and the camera. Unfortunately, the acquisition of accurate depth data is limited to indoor spaces and usually is tied to specific depth technologies and devices, thus limiting generalization capabilities. In this paper, we propose a method able to leverage the benefits of depth information without compromising its broader applicability and adaptability in a predominantly RGB-camera-centric landscape. Our approach consists of a heatmap-based 3D pose estimator that, leveraging the paradigm of Privileged Information, is able to hallucinate depth information from the RGB frames given at inference time. More precisely, depth information is used exclusively during training by enforcing our RGB-based hallucination network to learn similar features to a backbone pre-trained only on depth data. This approach proves to be effective even when dealing with limited and small datasets. Experimental results reveal that the paradigm of Privileged Information significantly enhances the model's performance, enabling efficient extraction of depth information by using only RGB images.

Davide Di Nucci, Riccardo Catalini, Guido Borghi et al.

Recent advances in 3D reconstruction and neural rendering,particularly 3D Gaussian Splatting, make it feasible and simple to edit 3D scenes and re-render them as highly realistic images. Therefore, security concerns arise regarding the authenticity of 3D content. Despite this threat, 3D fake detection remains largely unexplored in the literature, and most existing work is limited to 2D space. Therefore, in this paper, we formalize the concept of 3D fake detection and introduce Fake3DGS, a dataset of 3D Gaussian splatting scenes and corresponding rendered views, where fake images are produced by controlled manipulations of geometry, appearance, and spatial layout, while preserving high visual realism. Using this benchmark, we demonstrate that current state-of-the-art 2D detectors struggle to distinguish between original and 3D manipulated images. To bridge this gap, we introduce a 3D-aware detection method that leverages multi-view coherence and features derived from the Gaussian splatting representation. Experimental results demonstrate a substantial improvement in recognizing modified 3D content, underscoring the validity of the new dataset and the necessity for authenticity assessment techniques that extend beyond 2D evidence. Code and data are publicly released for future investigations.

Alessandro Simoni, Riccardo Catalini, Davide Di Nucci et al.

Depth ambiguity and joint uncertainty are the two main obstacles in obtaining accurate human pose predictions by 2D-to-3D lifting methods proposed in the literature. In particular, these issues are caused by 2D joint locations that can be mapped to multiple 3D positions, inducing multiple possible final poses. Following these considerations, we propose leveraging diffusion-based models generation capability to predict multiple hypotheses and aggregate them in a final accurate pose. Therefore, we introduce SnapPose3D, a pose-lifting framework trained deterministically to denoise 3D poses conditioned on both visual context and 2D pose features. SnapPose3D adopts a probabilistic approach during inference, generating multiple hypotheses through random sampling from a unit Gaussian distribution. Unlike most previous methods that address pose ambiguity by processing temporal sequences, SnapPose3D uses single frames as input, avoiding tracking and limiting computational cost, data acquisition complexity, and the need for online, real-time applications. We extensively evaluate SnapPose3D on well-known benchmarks for the 3D human pose estimation task showing its ability to generate and aggregate accurate hypotheses that lead to state-of-the-art results.

Riccardo Catalini, Davide Di Nucci, Guido Borghi et al.

We introduce GazeD, a new 3D gaze estimation method that jointly provides 3D gaze and human pose from a single RGB image. Leveraging the ability of diffusion models to deal with uncertainty, it generates multiple plausible 3D gaze and pose hypotheses based on the 2D context information extracted from the input image. Specifically, we condition the denoising process on the 2D pose, the surroundings of the subject, and the context of the scene. With GazeD we also introduce a novel way of representing the 3D gaze by positioning it as an additional body joint at a fixed distance from the eyes. The rationale is that the gaze is usually closely related to the pose, and thus it can benefit from being jointly denoised during the diffusion process. Evaluations across three benchmark datasets demonstrate that GazeD achieves state-of-the-art performance in 3D gaze estimation, even surpassing methods that rely on temporal information. Project details will be available at https://aimagelab.ing.unimore.it/go/gazed.

Davide Di Nucci, Matteo Tomei, Guido Borghi et al.

Accurate 3D reconstruction of vehicles is vital for applications such as vehicle inspection, predictive maintenance, and urban planning. Existing methods like Neural Radiance Fields and Gaussian Splatting have shown impressive results but remain limited by their reliance on dense input views, which hinders real-world applicability. This paper addresses the challenge of reconstructing vehicles from sparse-view inputs, leveraging depth maps and a robust pose estimation architecture to synthesize novel views and augment training data. Specifically, we enhance Gaussian Splatting by integrating a selective photometric loss, applied only to high-confidence pixels, and replacing standard Structure-from-Motion pipelines with the DUSt3R architecture to improve camera pose estimation. Furthermore, we present a novel dataset featuring both synthetic and real-world public transportation vehicles, enabling extensive evaluation of our approach. Experimental results demonstrate state-of-the-art performance across multiple benchmarks, showcasing the method's ability to achieve high-quality reconstructions even under constrained input conditions.

Daniel Rossi, Guido Borghi, Roberto Vezzani

Designing efficient neural networks for embedded devices is a critical challenge, particularly in applications requiring real-time performance, such as aerial imaging with drones and UAVs for emergency responses. In this work, we introduce TakuNet, a novel light-weight architecture which employs techniques such as depth-wise convolutions and an early downsampling stem to reduce computational complexity while maintaining high accuracy. It leverages dense connections for fast convergence during training and uses 16-bit floating-point precision for optimization on embedded hardware accelerators. Experimental evaluation on two public datasets shows that TakuNet achieves near-state-of-the-art accuracy in classifying aerial images of emergency situations, despite its minimal parameter count. Real-world tests on embedded devices, namely Jetson Orin Nano and Raspberry Pi, confirm TakuNet's efficiency, achieving more than 650 fps on the 15W Jetson board, making it suitable for real-time AI processing on resource-constrained platforms and advancing the applicability of drones in emergency scenarios. The code and implementation details are publicly released.

Alessandro Simoni, Stefano Pini, Roberto Vezzani et al.

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.

Ariel Caputo, Andrea Giachetti, Simone Soso et al.

Gesture recognition is a fundamental tool to enable novel interaction paradigms in a variety of application scenarios like Mixed Reality environments, touchless public kiosks, entertainment systems, and more. Recognition of hand gestures can be nowadays performed directly from the stream of hand skeletons estimated by software provided by low-cost trackers (Ultraleap) and MR headsets (Hololens, Oculus Quest) or by video processing software modules (e.g. Google Mediapipe). Despite the recent advancements in gesture and action recognition from skeletons, it is unclear how well the current state-of-the-art techniques can perform in a real-world scenario for the recognition of a wide set of heterogeneous gestures, as many benchmarks do not test online recognition and use limited dictionaries. This motivated the proposal of the SHREC 2021: Track on Skeleton-based Hand Gesture Recognition in the Wild. For this contest, we created a novel dataset with heterogeneous gestures featuring different types and duration. These gestures have to be found inside sequences in an online recognition scenario. This paper presents the result of the contest, showing the performances of the techniques proposed by four research groups on the challenging task compared with a simple baseline method.

Matteo Fabbri, Guido Borghi, Fabio Lanzi et al.

Can faces acquired by low-cost depth sensors be useful to catch some characteristic details of the face? Typically the answer is no. However, new deep architectures can generate RGB images from data acquired in a different modality, such as depth data. In this paper, we propose a new \textit{Deterministic Conditional GAN}, trained on annotated RGB-D face datasets, effective for a face-to-face translation from depth to RGB. Although the network cannot reconstruct the exact somatic features for unknown individual faces, it is capable to reconstruct plausible faces; their appearance is accurate enough to be used in many pattern recognition tasks. In fact, we test the network capability to hallucinate with some \textit{Perceptual Probes}, as for instance face aspect classification or landmark detection. Depth face can be used in spite of the correspondent RGB images, that often are not available due to difficult luminance conditions. Experimental results are very promising and are as far as better than previously proposed approaches: this domain translation can constitute a new way to exploit depth data in new future applications.

Stefano Pini, Guido Borghi, Roberto Vezzani

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 traditional cameras, their use is partially prevented by the limited applicability of traditional data processing and vision algorithms. To this aim, we present a framework which exploits the output stream of event cameras to synthesize RGB frames, relying on an initial or a periodic set of color key-frames and the sequence of intermediate events. Differently from existing work, we propose a deep learning-based frame synthesis method, consisting of an adversarial architecture combined with a recurrent module. Qualitative results and quantitative per-pixel, perceptual, and semantic evaluation on four public datasets confirm the quality of the synthesized images.

Stefano Pini, Filippo Grazioli, Guido Borghi et al.

In this paper, an adversarial architecture for facial depth map estimation from monocular intensity images is presented. By following an image-to-image approach, we combine the advantages of supervised learning and adversarial training, proposing a conditional Generative Adversarial Network that effectively learns to translate intensity face images into the corresponding depth maps. Two public datasets, namely Biwi database and Pandora dataset, are exploited to demonstrate that the proposed model generates high-quality synthetic depth images, both in terms of visual appearance and informative content. Furthermore, we show that the model is capable of predicting distinctive facial details by testing the generated depth maps through a deep model trained on authentic depth maps for the face verification task.

Matteo Fabbri, Fabio Lanzi, Simone Calderara et al.

Multi-People Tracking in an open-world setting requires a special effort in precise detection. Moreover, temporal continuity in the detection phase gains more importance when scene cluttering introduces the challenging problems of occluded targets. For the purpose, we propose a deep network architecture that jointly extracts people body parts and associates them across short temporal spans. Our model explicitly deals with occluded body parts, by hallucinating plausible solutions of not visible joints. We propose a new end-to-end architecture composed by four branches (visible heatmaps, occluded heatmaps, part affinity fields and temporal affinity fields) fed by a time linker feature extractor. To overcome the lack of surveillance data with tracking, body part and occlusion annotations we created the vastest Computer Graphics dataset for people tracking in urban scenarios by exploiting a photorealistic videogame. It is up to now the vastest dataset (about 500.000 frames, almost 10 million body poses) of human body parts for people tracking in urban scenarios. Our architecture trained on virtual data exhibits good generalization capabilities also on public real tracking benchmarks, when image resolution and sharpness are high enough, producing reliable tracklets useful for further batch data association or re-id modules.

Guido Borghi, Matteo Fabbri, Roberto Vezzani et al.

Depth cameras allow to set up reliable solutions for people monitoring and behavior understanding, especially when unstable or poor illumination conditions make unusable common RGB sensors. Therefore, we propose a complete framework for the estimation of the head and shoulder pose based on depth images only. A head detection and localization module is also included, in order to develop a complete end-to-end system. The core element of the framework is a Convolutional Neural Network, called POSEidon+, that receives as input three types of images and provides the 3D angles of the pose as output. Moreover, a Face-from-Depth component based on a Deterministic Conditional GAN model is able to hallucinate a face from the corresponding depth image. We empirically demonstrate that this positively impacts the system performances. We test the proposed framework on two public datasets, namely Biwi Kinect Head Pose and ICT-3DHP, and on Pandora, a new challenging dataset mainly inspired by the automotive setup. Experimental results show that our method overcomes several recent state-of-art works based on both intensity and depth input data, running in real-time at more than 30 frames per second.

Diego Ballotta, Guido Borghi, Roberto Vezzani et al.

Head detection and localization is a demanding task and a key element for many computer vision applications, like video surveillance, Human Computer Interaction and face analysis. The stunning amount of work done for detecting faces on RGB images, together with the availability of huge face datasets, allowed to setup very effective systems on that domain. However, due to illumination issues, infrared or depth cameras may be required in real applications. In this paper, we introduce a novel method for head detection on depth images that exploits the classification ability of deep learning approaches. In addition to reduce the dependency on the external illumination, depth images implicitly embed useful information to deal with the scale of the target objects. Two public datasets have been exploited: the first one, called Pandora, is used to train a deep binary classifier with face and non-face images. The second one, collected by Cornell University, is used to perform a cross-dataset test during daily activities in unconstrained environments. Experimental results show that the proposed method overcomes the performance of state-of-art methods working on depth images.

Marco Venturelli, Guido Borghi, Roberto Vezzani et al.

The correct estimation of the head pose is a problem of the great importance for many applications. For instance, it is an enabling technology in automotive for driver attention monitoring. In this paper, we tackle the pose estimation problem through a deep learning network working in regression manner. Traditional methods usually rely on visual facial features, such as facial landmarks or nose tip position. In contrast, we exploit a Convolutional Neural Network (CNN) to perform head pose estimation directly from depth data. We exploit a Siamese architecture and we propose a novel loss function to improve the learning of the regression network layer. The system has been tested on two public datasets, Biwi Kinect Head Pose and ICT-3DHP database. The reported results demonstrate the improvement in accuracy with respect to current state-of-the-art approaches and the real time capabilities of the overall framework.

Guido Borghi, Roberto Vezzani, Rita Cucchiara

HMMs are widely used in action and gesture recognition due to their implementation simplicity, low computational requirement, scalability and high parallelism. They have worth performance even with a limited training set. All these characteristics are hard to find together in other even more accurate methods. In this paper, we propose a novel double-stage classification approach, based on Multiple Stream Discrete Hidden Markov Models (MSD-HMM) and 3D skeleton joint data, able to reach high performances maintaining all advantages listed above. The approach allows both to quickly classify pre-segmented gestures (offline classification), and to perform temporal segmentation on streams of gestures (online classification) faster than real time. We test our system on three public datasets, MSRAction3D, UTKinect-Action and MSRDailyAction, and on a new dataset, Kinteract Dataset, explicitly created for Human Computer Interaction (HCI). We obtain state of the art performances on all of them.

Marco Venturelli, Guido Borghi, Roberto Vezzani et al.

Recently, deep learning approaches have achieved promising results in various fields of computer vision. In this paper, we tackle the problem of head pose estimation through a Convolutional Neural Network (CNN). Differently from other proposals in the literature, the described system is able to work directly and based only on raw depth data. Moreover, the head pose estimation is solved as a regression problem and does not rely on visual facial features like facial landmarks. We tested our system on a well known public dataset, Biwi Kinect Head Pose, showing that our approach achieves state-of-art results and is able to meet real time performance requirements.

Guido Borghi, Marco Venturelli, Roberto Vezzani et al.

Fast and accurate upper-body and head pose estimation is a key task for automatic monitoring of driver attention, a challenging context characterized by severe illumination changes, occlusions and extreme poses. In this work, we present a new deep learning framework for head localization and pose estimation on depth images. The core of the proposal is a regression neural network, called POSEidon, which is composed of three independent convolutional nets followed by a fusion layer, specially conceived for understanding the pose by depth. In addition, to recover the intrinsic value of face appearance for understanding head position and orientation, we propose a new Face-from-Depth approach for learning image faces from depth. Results in face reconstruction are qualitatively impressive. We test the proposed framework on two public datasets, namely Biwi Kinect Head Pose and ICT-3DHP, and on Pandora, a new challenging dataset mainly inspired by the automotive setup. Results show that our method overcomes all recent state-of-art works, running in real time at more than 30 frames per second.