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.
Filters
Increasing 3D Resolution of Kinect Faces
[chapter]
2015
Lecture Notes in Computer Science
Preserved Fulltext
Based on these considerations, in this paper we define an approach for reconstructing a higher-resolution 3D face model from a sequence of low-resolution 3D scans. ...
Measures of the quality of the reconstructed models with respect to high-resolution scans and in comparison with two alternative techniques, demonstrate the viability of the proposed solution. ...
Fig. 5 . 5 Sample of the The Florence face dataset: (a) 3D high-resolution scan; (b) RGB and depth frames from the Kinect video sequence, with the head pose changing from frontal to left and right side ...
doi:10.1007/978-3-319-16178-5_45
fatcat:q6wbezjyrff35krpe4z3zphejm
Kinect-based automatic 3D high-resolution face modeling
2012
2012 International Conference on Image Analysis and Signal Processing
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 2016; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose a novel scheme for automatically and efficiently constructing a life-like textured 3D high-resolution model for the face of any user in front of a Kinect. ...
Specifically, this scheme is composed of a sequence of steps including head region segmentation, depth and color image registration, resolution enhancement and 3D model fairing. ...
However, its low resolution, which is up to 640 ×480 of depth image still limits the smoothness and vividness for high resolution 3D modeling tasks and, in particular, high resolution 3D facial modeling ...
doi:10.1109/iasp.2012.6425065
fatcat:of22gkspabhmhlo6ofboq6l5fu
Superfaces: A Super-Resolution Model for 3D Faces
[chapter]
2012
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.
The approach is validated on a data set that includes, for each subject, one sequence of low-resolution 3D face scans and one ground-truth high-resolution 3D face model acquired through a high-resolution ...
In this paper, we define a super-resolution model for 3D faces by which a sequence of low-resolution 3D scans can be processed to extract a higher resolution 3D face model, namely the superface model. ...
The authors acknowledge Lorenzo Seidenari for his valuable contribute to the design and development of the software modules for 3D data acquisition through the Kinect scanner. ...
doi:10.1007/978-3-642-33863-2_8
fatcat:oepfmsxqkje6lmhtndyvs243jm
Implementation of 3D object reconstruction using a pair of Kinect cameras
2014
Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific
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.
We reconstruct depth data in the integrated 3D space and obtain a 3D object model at 5 fps. ...
After we refine raw depth images from two Kinect cameras using a joint bilateral filter, we find intrinsic and extrinsic parameters by camera calibration. ...
Kinect is a 3D vision camera released from Microsoft and it has a high performance camera and many users but relatively low prices. ...
doi:10.1109/apsipa.2014.7041651
dblp:conf/apsipa/ShinH14
fatcat:jbfynmwaufchfcmobiu7qzvcn4
Detailed Full-Body Reconstructions of Moving People from Monocular RGB-D Sequences
2015
2015 IEEE International Conference on Computer Vision (ICCV)
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.
Our novel body model has variable shape detail, allowing it to capture faces with a high-resolution deformable head model and body shape with lower-resolution. ...
Figure 1 : From a monocular RGB-D sequence (background), we estimate a low-dimensional parametric model of body shape (left), detailed 3D shape (middle), and a high-resolution texture map (right). ...
[19] reconstruct non-rigid surface deformations from high-resolution monocular depth scans, using a smooth template as a geometric prior. Zollhöfer et al. ...
doi:10.1109/iccv.2015.265
dblp:conf/iccv/BogoBL015
fatcat:zl7z2nhxynguvexakefzdw74va
3D Face Model Super-Resolution Based on Radial Curve Estimation
2020
Applied Sciences
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 present a super-resolution method for reconstructing a high resolution 3D face model from a low resolution 3D face model acquired from a consumer depth camera. ...
Finally, a reference high resolution 3D face model was deformed to generate a high resolution face model by using the radial curves as the constraining feature. ...
Methods in [2, [6] [7] [8] reduce the noise in depth data by aligning multiple scans to construct a high resolution 3D model, where Kinect Fusion [2] is a classical real-time 3D reconstruction method ...
doi:10.3390/app10031047
fatcat:wjtfnne5ynbcpkldlvvfkidcsm
Generating Super-Resolved Depth Maps Using Low-Cost Sensors and RGB Images
[chapter]
2014
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 2020; you can also visit the original URL.
The file type is application/pdf.
There are a lot of three-dimensional reconstruction applications of real scenes. ...
Studying that attempts, this work suggests the modification of super-resolution algorithm described by Mitzel et al. [1] in order to consider in its calculations colored images provided by Kinect. ...
Super-resolution generates high resolution from N low resolution depth maps. The global rigid registration originates a 3D mesh reconstructed from the high-resolution maps. ...
doi:10.1007/978-3-319-14364-4_61
fatcat:26imk2n4zzdv5ihezvfozwlv2a
HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications. ...
In this work, we contribute HuMMan, a large-scale multi-modal 4D human dataset with 1000 human subjects, 400k sequences and 60M frames. ...
Azure Kinect is popular with both academia and the industry with a color resolution of 1920×1080, and a depth resolution of 640×576. We deploy ten Kinects to capture multi-view RGB-D sequences. ...
arXiv:2204.13686v1
fatcat:d6ur54bgfjbofle3htqg3firb4
Compact and Accurate 3-D Face Modeling Using an RGB-D Camera: Let's Open the Door to 3-D Video Conference
2013
2013 IEEE International Conference on Computer Vision Workshops
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.
We present a method for producing an accurate and compact 3-D face model in real time using a low cost RGB-D sensor like the Kinect camera. ...
We extend and use Bump Images for highly accurate and low memory consumption 3-D reconstruction of the human face. ...
Our goal is to develop a method that enables live high-quality 3-D face model reconstruction from a consumer RGB-D camera while maintaining low memory use. ...
doi:10.1109/iccvw.2013.16
dblp:conf/iccvw/AnasosaluTS13
fatcat:eo2zo7qtx5afdg4gl7pe4m52wi
Accurate and Robust 3D Facial Capture Using a Single RGBD Camera
2013
2013 IEEE 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 2016; you can also visit the original URL.
The file type is application/pdf.
features detected from single RGBD images. ...
In particular, we develop a robust and accurate image-based nonrigid registration algorithm that incrementally deforms a 3D template mesh model to best match observed depth image data and important facial ...
Overview Our system acquires high-quality 3D facial models from single RGBD images recorded by a single Kinect. ...
doi:10.1109/iccv.2013.449
dblp:conf/iccv/ChenWSTC13
fatcat:gdqazymuljcarc4y25xxurasji
Real-time encoding of live reconstructed mesh sequences for 3D tele-immersion
2013
2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)
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.
In this paper we experiment with a real-time reconstruction system that outputs a sequence of triangular meshes. ...
Comparison with the SC3DMC standard on the live reconstructed mesh sequences reveals an encoding speedup of over 20 times at comparable rate/distortion levels. ...
The high-resolution reconstruction data contains around 250,000 vertices per model (N=24 reconstructed models) and the low-resolution data approximately 28,000 points (with N=26 reconstructed models). ...
doi:10.1109/icmew.2013.6618356
dblp:conf/icmcs/MekuriaADC13
fatcat:hhobrryjxndr3hrlod7bjmo4yy
Effective Key Region-Guided Face Detail Optimization Algorithm for 3D Face Reconstruction
2022
Journal of Sensors
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 2022; you can also visit the original URL.
The file type is application/pdf.
While the Kinect, a typical low-cost 3D data collection device, has been widely used in many applications, in this work, we propose a highly efficient 3D face point cloud optimization method for face reconstruction ...
Low-cost and highly efficient 3D face reconstruction is a significant technique for developing virtual interaction applications. ...
Bondi et al. used Kinect as a low-resolution scanner to reconstruct high-resolution face models by computing the 3D face registration among depth face sequences [65] . ...
doi:10.1155/2022/3419951
doaj:f802666df23349b1b4be3b46eb2e850e
fatcat:mn73qne7enhrte54cjy5yo6ccy
Patches Detection and Fusion for 3D Face Cloning
2015
Advances In Image and Video Processing
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.
We fit a 3D Morphable Face Model on each frame to eliminate noise, increase resolution and provide a structured mesh. ...
3D face clones are used in many fields such as video games and Human-Computer Interaction. However, high-resolution sensors generating high quality clones are expensive and not accessible to all. ...
M.Zollhöfer et al [21] present an algorithm for 3D clones from high resolution RGB and depth data obtained with a Kinect camera. ...
doi:10.14738/aivp.35.814
fatcat:lfanad2bongblhirb5zuuzq4zq
Person Re-Identification from Depth Cameras using Skeleton and 3D Face Data
[article]
2018
Eurographics Workshop on 3D Object Retrieval, EG 3DOR
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 2022; you can also visit the original URL.
The file type is application/pdf.
Unfortunately, face and skeleton quality is not always enough to grant a correct recognition from depth data. Both features are affected by the pose of the subject and the distance from the camera. ...
Our method combining face and skeleton data improves rank-1 accuracy compared to individual cues especially on short realistic sequences. ...
We showed how reconstructed faces with increased resolution can be derived from low-resolution depth frames, and as the resulting cumulated observed model can be used to recognize people very effectively ...
doi:10.2312/3dor.20181058
fatcat:qfwdesdotzfndb6lkupfxjvepe
Augmenting Depth Camera Output Using Photometric Stereo
2011
IAPR International Workshop on Machine Vision Applications
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 2022; you can also visit the original URL.
The file type is application/pdf.
Improved reconstruction is demonstrated using the Kinect's inbuilt RGB camera and further improvements are achieved by introducing an additional high resolution camera. ...
We present a system for augmenting depth camera output using multispectral photometric stereo. ...
Reconstruction of a dynamic sequence using (a) the depth camera only and (b) the depth camera combined with photometric stereo applied to the image from the inbuilt Kinect color camera (c). ...
dblp:conf/mva/AndersonSC11
fatcat:kvmldvbvvfh63bgalwerzn74uu
« Previous
Showing results 1 — 15 out of 2,200 results