A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Uncalibrated 3D Room Reconstruction from Sound
[article]
2016
arXiv
pre-print
Preserved Fulltext
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]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
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
arXiv:2104.10609v1
fatcat:tjg6irszhjf47k3ecj56h27vge
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 https://iit-pavis.github.io/lifting_events_to_3d_hpe.
Manifold Constrained Low-Rank Decomposition
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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
arXiv:1708.01846v1
fatcat:4m6bk2xjrfgvbh6miqsxffuugy
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.
Towards Fully Uncalibrated Room Reconstruction With Sound
2014
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Publication in the conference proceedings of EUSIPCO, Lisbon, Portugal, 2014
doi:10.5281/zenodo.43892
fatcat:k2yg7pwyazbmnd7az5pbflbdr4
Objects Localisation from Motion with Constraints
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2018 pre-print arXiv:1803.10474v1 fatcat:gmq54g6ifzb5pklafpruh6aipy
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
arXiv:1803.10474v2
fatcat:wwrngte7snanhnoudbk3zzhrfe
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.
Room Impulse Response Estimation By Iterative Weighted L1-Norm
2015
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Publication in the conference proceedings of EUSIPCO, Nice, France, 2015
doi:10.5281/zenodo.38905
fatcat:myap76h4yvckjktrqn3orh64tu
Multiview 3D warps
2011
2011 International Conference on Computer Vision
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
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
doi:10.1109/iccv.2011.6126303
dblp:conf/iccv/BueB11
fatcat:tebvprnkzfe3vani6ay4pvo5ty
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.
Consistent Mesh Colors for Multi-View Reconstructed 3D Scenes
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
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
arXiv:2101.10734v1
fatcat:3kxi36pdoja4hlthdooiehwvau
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.
Non-Rigid Stereo Factorization
2006
International Journal of Computer Vision
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
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
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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
arXiv:2004.08270v1
fatcat:6uqdkpyofzcyvd3phdbo4g6vxu
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.
Complex-Object Visual Inspection via Multiple Lighting Configurations
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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,
arXiv:2004.09374v1
fatcat:jwkunfwmdzbjbo42ymz5ystjru
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.
Extracting Average Shapes from Occluded Non-rigid Motion
[chapter]
2007
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
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
doi:10.1007/978-3-540-72849-8_28
fatcat:sza7houdhbbyplahg2tgfjv5fe
more »
... th real and synthetic sequences show the procedure effectiveness in dealing with different degrees of occlusions in the measurements.
Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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
arXiv:2006.11812v1
fatcat:d5pdt6dmlzehboxavtw4fmnz4e
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.
« Previous
Showing results 1 — 15 out of 224 results