224 Hits in 1.6 sec

Uncalibrated 3D Room Reconstruction from Sound [article]

Marco Crocco, Andrea Trucco, Alessio Del Bue
2016 arXiv   pre-print
Instead, the approach of Crocco and Del Bue [10] define the room geometry estimation problem as an optimization problem without any a priori information (apart from the room convexity assumption).  ... 
arXiv:1606.06258v1 fatcat:adyu534gqbcqvnx6uz75vhs5b4

The Visual Social Distancing Problem [article]

Marco Cristani, Alessio Del Bue, Vittorio Murino, Francesco Setti, Alessandro Vinciarelli
2020 arXiv   pre-print
Del Bue is within Pattern Analysis and Computer Vision (PAVIS) research line of the Istituto Italiano di Tecnologia (IIT); V.  ... 
arXiv:2005.04813v1 fatcat:quoqdw2geva5tm5aaavyvv2epu

Lifting Monocular Events to 3D Human Poses [article]

Gianluca Scarpellini, Pietro Morerio, Alessio Del Bue
2021 arXiv   pre-print
This paper presents a novel 3D human pose estimation approach using a single stream of asynchronous events as input. Most of the state-of-the-art approaches solve this task with RGB cameras, however struggling when subjects are moving fast. On the other hand, event-based 3D pose estimation benefits from the advantages of event-cameras, especially their efficiency and robustness to appearance changes. Yet, finding human poses in asynchronous events is in general more challenging than standard
more » ... pose estimation, since little or no events are triggered in static scenes. Here we propose the first learning-based method for 3D human pose from a single stream of events. Our method consists of two steps. First, we process the event-camera stream to predict three orthogonal heatmaps per joint; each heatmap is the projection of of the joint onto one orthogonal plane. Next, we fuse the sets of heatmaps to estimate 3D localisation of the body joints. As a further contribution, we make available a new, challenging dataset for event-based human pose estimation by simulating events from the RGB Human3.6m dataset. Experiments demonstrate that our method achieves solid accuracy, narrowing the performance gap between standard RGB and event-based vision. The code is freely available at
arXiv:2104.10609v1 fatcat:tjg6irszhjf47k3ecj56h27vge

Manifold Constrained Low-Rank Decomposition [article]

Chen Chen and Baochang Zhang and Alessio Del Bue and Vittorio Murino
2017 arXiv   pre-print
Low-rank decomposition (LRD) is a state-of-the-art method for visual data reconstruction and modelling. However, it is a very challenging problem when the image data contains significant occlusion, noise, illumination variation, and misalignment from rotation or viewpoint changes. We leverage the specific structure of data in order to improve the performance of LRD when the data are not ideal. To this end, we propose a new framework that embeds manifold priors into LRD. To implement the
more » ... k, we design an alternating direction method of multipliers (ADMM) method which efficiently integrates the manifold constraints during the optimization process. The proposed approach is successfully used to calculate low-rank models from face images, hand-written digits and planar surface images. The results show a consistent increase of performance when compared to the state-of-the-art over a wide range of realistic image misalignments and corruptions.
arXiv:1708.01846v1 fatcat:4m6bk2xjrfgvbh6miqsxffuugy

Towards Fully Uncalibrated Room Reconstruction With Sound

Marco Crocco, Alessio Del Bue, V. Murino, A. Trucco
2014 Zenodo  
Publication in the conference proceedings of EUSIPCO, Lisbon, Portugal, 2014
doi:10.5281/zenodo.43892 fatcat:k2yg7pwyazbmnd7az5pbflbdr4

Objects Localisation from Motion with Constraints [article]

Paul Gay, Alessio Del Bue
2018 arXiv   pre-print
This paper presents a method to estimate the 3D object position and occupancy given a set of object detections in multiple images and calibrated cameras. This problem is modelled as the estimation of a set of quadrics given 2D conics fit to the object bounding boxes. Although a closed form solution has been recently proposed, the resulting quadrics can be inaccurate or even be non valid ellipsoids in presence of noisy and inaccurate detections. This effect is especially important in case of
more » ... l baselines, resulting in dramatic failures. To cope with this problem, we propose a set of linear constraints by matching the centres of the reprojected quadrics with the centres of the observed conics. These constraints can be solved with a linear system thus providing a more computationally efficient solution with respect to a non-linear alternative. Experiments on real data show that the proposed approach improves significantly the accuracy and the validity of the ellipsoids.
arXiv:1803.10474v2 fatcat:wwrngte7snanhnoudbk3zzhrfe

Room Impulse Response Estimation By Iterative Weighted L1-Norm

Marco Crocco, Alessio Del Bue
2015 Zenodo  
Publication in the conference proceedings of EUSIPCO, Nice, France, 2015
doi:10.5281/zenodo.38905 fatcat:myap76h4yvckjktrqn3orh64tu

Multiview 3D warps

Alessio Del Bue, Adrien Bartoli
2011 2011 International Conference on Computer Vision  
Image registration and 3D reconstruction are fundamental computer vision and medical imaging problems. They are particularly challenging when the input data are images of a deforming body obtained by a single moving camera. We propose a new modelling framework, the multiview 3D warps. Existing models are twofold: they estimate interimage warps which are often inconsistent between the different images and do not model the underlying 3D structure, or reconstruct just a sparse set of points. In
more » ... trast, our multiview 3D warps combine the advantages of both; they have an explicit 3D component and a set of 3D deformations combined with projection to 2D. They thus capture the dense deforming body's time-varying shape and camera pose. The advantages over the classical solutions are numerous: thanks to our feature-based estimation method for the multiview 3D warps, one can not only augment the original images but also retarget or clone the observed body's 3D deformations by changing the pose. Experimental results on simulated and real data are reported, confirming the advantages of our framework over existing methods.
doi:10.1109/iccv.2011.6126303 dblp:conf/iccv/BueB11 fatcat:tebvprnkzfe3vani6ay4pvo5ty

Consistent Mesh Colors for Multi-View Reconstructed 3D Scenes [article]

Mohamed Dahy Elkhouly, Alessio Del Bue, Stuart James
2021 arXiv   pre-print
We address the issue of creating consistent mesh texture maps captured from scenes without color calibration. We find that the method for aggregation of the multiple views is crucial for creating spatially consistent meshes without the need to explicitly optimize for spatial consistency. We compute a color prior from the cross-correlation of observable view faces and the faces per view to identify an optimal per-face color. We then use this color in a re-weighting ratio for the best-view
more » ... , which is identified by prior mesh texturing work, to create a spatial consistent texture map. Despite our method not explicitly handling spatial consistency, our results show qualitatively more consistent results than other state-of-the-art techniques while being computationally more efficient. We evaluate on prior datasets and additionally Matterport3D showing qualitative improvements.
arXiv:2101.10734v1 fatcat:3kxi36pdoja4hlthdooiehwvau

Non-Rigid Stereo Factorization

Alessio Del Bue, Lourdes Agapito
2006 International Journal of Computer Vision  
Alessio Del Bue holds a Queen Mary Studentship award.  ...  Bue and Agapito where R f = r f,1 r f,2 r f,3 r f,4 r f,5 r f,6 (2) is a 2 × 3 matrix which contains the first and second rows of the camera rotation matrix and T f contains the first two components of  ...  image points observed at each frame f are related to the coordinates of the 3D points according to the following equation: W f = u f,1 . . . u f,P v f,1 . . . v f,P = R f K i=1 l f,i S i + T f (1) 196 Del  ... 
doi:10.1007/s11263-005-3958-5 fatcat:eaafbiqj6zczre6nyuajhwloq4

The Visual Social Distancing Problem

Marco Cristani, Alessio Del Bue, Vittorio Murino, Francesco Setti, Alessandro Vinciarelli
2020 IEEE Access  
ALESSIO DEL BUE (Member, IEEE) is currently a Tenured Senior Researcher leading the Pattern Analyisis and computer VISion (PAVIS) Research Line, Italian Institute of Technology (IIT), Genoa, Italy.  ... 
doi:10.1109/access.2020.3008370 fatcat:2ceecrtvefb3lgn3hus2nycbwm

Weakly Supervised Geodesic Segmentation of Egyptian Mummy CT Scans [article]

Avik Hati, Matteo Bustreo, Diego Sona, Vittorio Murino, Alessio Del Bue
2020 arXiv   pre-print
In this paper, we tackle the task of automatically analyzing 3D volumetric scans obtained from computed tomography (CT) devices. In particular, we address a particular task for which data is very limited: the segmentation of ancient Egyptian mummies CT scans. We aim at digitally unwrapping the mummy and identify different segments such as body, bandages and jewelry. The problem is complex because of the lack of annotated data for the different semantic regions to segment, thus discouraging the
more » ... se of strongly supervised approaches. We, therefore, propose a weakly supervised and efficient interactive segmentation method to solve this challenging problem. After segmenting the wrapped mummy from its exterior region using histogram analysis and template matching, we first design a voxel distance measure to find an approximate solution for the body and bandage segments. Here, we use geodesic distances since voxel features as well as spatial relationship among voxels is incorporated in this measure. Next, we refine the solution using a GrabCut based segmentation together with a tracking method on the slices of the scan that assigns labels to different regions in the volume, using limited supervision in the form of scribbles drawn by the user. The efficiency of the proposed method is demonstrated using visualizations and validated through quantitative measures and qualitative unwrapping of the mummy.
arXiv:2004.08270v1 fatcat:6uqdkpyofzcyvd3phdbo4g6vxu

Complex-Object Visual Inspection via Multiple Lighting Configurations [article]

Maya Aghaei, Matteo Bustreo, Pietro Morerio, Nicolo Carissimi, Alessio Del Bue, Vittorio Murino
2020 arXiv   pre-print
The design of an automatic visual inspection system is usually performed in two stages. While the first stage consists in selecting the most suitable hardware setup for highlighting most effectively the defects on the surface to be inspected, the second stage concerns the development of algorithmic solutions to exploit the potentials offered by the collected data. In this paper, first, we present a novel illumination setup embedding four illumination configurations to resemble diffused,
more » ... ld, and front lighting techniques. Second, we analyze the contributions brought by deploying the proposed setup in training phase only - mimicking the scenario in which an already developed visual inspection system cannot be modified on the customer site - and in evaluation phase. Along with an exhaustive set of experiments, in this paper, we demonstrate the suitability of the proposed setup for effective illumination of complex-objects, defined as manufactured items with variable surface characteristics that cannot be determined a priori. Moreover, we discuss the importance of multiple light configurations availability during training and their natural boosting effect which, without the need to modify the system design in evaluation phase, lead to improvements in the overall system performance.
arXiv:2004.09374v1 fatcat:jwkunfwmdzbjbo42ymz5ystjru

Extracting Average Shapes from Occluded Non-rigid Motion [chapter]

Alessio Del Bue
2007 Lecture Notes in Computer Science  
This paper presents a method to efficiently estimate average 3-D shapes from non-rigid motion in the case of missing data. Such a shape can be further used to accomplish full reconstruction of deformable objects and registration of non-rigid shapes. The approach is based firstly on a power method which linearly provides an initial estimate of the 3-D structure and motion components of the object shape. Secondly, non-linear optimisation is used to refine the initial linear estimation. Tests on
more » ... th real and synthetic sequences show the procedure effectiveness in dealing with different degrees of occlusions in the measurements.
doi:10.1007/978-3-540-72849-8_28 fatcat:sza7houdhbbyplahg2tgfjv5fe

Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning [article]

Giancarlo Paoletti, Jacopo Cavazza, Cigdem Beyan, Alessio Del Bue
2020 arXiv   pre-print
This paper tackles the problem of human action recognition, defined as classifying which action is displayed in a trimmed sequence, from skeletal data. Albeit state-of-the-art approaches designed for this application are all supervised, in this paper we pursue a more challenging direction: Solving the problem with unsupervised learning. To this end, we propose a novel subspace clustering method, which exploits covariance matrix to enhance the action's discriminability and a timestamp pruning
more » ... roach that allow us to better handle the temporal dimension of the data. Through a broad experimental validation, we show that our computational pipeline surpasses existing unsupervised approaches but also can result in favorable performances as compared to supervised methods.
arXiv:2006.11812v1 fatcat:d5pdt6dmlzehboxavtw4fmnz4e
« Previous Showing results 1 — 15 out of 224 results