Sorry, you need to enable JavaScript to visit this website.

Image, Video, and Multidimensional Signal Processing

Immersive Optical-See-Through Augmented Reality (Keynote Talk)


Immersive Optical-See-Through Augmented Reality. Augmented Reality has been getting ready for the last 20 years, and is finally becoming real, powered by progress in enabling technologies such as graphics, vision, sensors, and displays. In this talk I’ll provide a personal retrospective on my journey, working on all those enablers, getting ready for the coming AR revolution. At Meta, we are working on immersive optical-see-through AR headset, as well as the full software stack. We’ll discuss the differences of optical vs.

Paper Details

Authors:
Kari Pulli
Submitted On:
22 December 2017 - 1:30pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP_2017_Meta_AR_small.pdf

(455)

Subscribe

[1] Kari Pulli, "Immersive Optical-See-Through Augmented Reality (Keynote Talk)", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2261. Accessed: Dec. 02, 2020.
@article{2261-17,
url = {http://sigport.org/2261},
author = {Kari Pulli },
publisher = {IEEE SigPort},
title = {Immersive Optical-See-Through Augmented Reality (Keynote Talk)},
year = {2017} }
TY - EJOUR
T1 - Immersive Optical-See-Through Augmented Reality (Keynote Talk)
AU - Kari Pulli
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2261
ER -
Kari Pulli. (2017). Immersive Optical-See-Through Augmented Reality (Keynote Talk). IEEE SigPort. http://sigport.org/2261
Kari Pulli, 2017. Immersive Optical-See-Through Augmented Reality (Keynote Talk). Available at: http://sigport.org/2261.
Kari Pulli. (2017). "Immersive Optical-See-Through Augmented Reality (Keynote Talk)." Web.
1. Kari Pulli. Immersive Optical-See-Through Augmented Reality (Keynote Talk) [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2261

Lossless Video Coding Based on Probability Model Optimization Utilizing Example Search and Adaptive Prediction

Paper Details

Authors:
Submitted On:
12 November 2020 - 7:49pm
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

ICIP2020_unno_r3.pdf

(10)

Subscribe

[1] , "Lossless Video Coding Based on Probability Model Optimization Utilizing Example Search and Adaptive Prediction", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5552. Accessed: Dec. 02, 2020.
@article{5552-20,
url = {http://sigport.org/5552},
author = { },
publisher = {IEEE SigPort},
title = {Lossless Video Coding Based on Probability Model Optimization Utilizing Example Search and Adaptive Prediction},
year = {2020} }
TY - EJOUR
T1 - Lossless Video Coding Based on Probability Model Optimization Utilizing Example Search and Adaptive Prediction
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5552
ER -
. (2020). Lossless Video Coding Based on Probability Model Optimization Utilizing Example Search and Adaptive Prediction. IEEE SigPort. http://sigport.org/5552
, 2020. Lossless Video Coding Based on Probability Model Optimization Utilizing Example Search and Adaptive Prediction. Available at: http://sigport.org/5552.
. (2020). "Lossless Video Coding Based on Probability Model Optimization Utilizing Example Search and Adaptive Prediction." Web.
1. . Lossless Video Coding Based on Probability Model Optimization Utilizing Example Search and Adaptive Prediction [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5552

Skeleton Action Recognition Based on Singular Value Decomposition


This work introduces new method using the singular value decomposition (SVD) to recognise human activities from skeleton motion sequences. The primary focus was on different activity durations, inaccurate placement of the joints and loss of information about position of the joints. For that we needed to develop a robust model. At first, the pose features are created for description of skeleton pose per frame, that is created by directional vectors to alljoint pairwise combinations without repetition.

Paper Details

Authors:
Submitted On:
10 November 2020 - 9:39am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2666.pdf

(11)

Subscribe

[1] , "Skeleton Action Recognition Based on Singular Value Decomposition", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5551. Accessed: Dec. 02, 2020.
@article{5551-20,
url = {http://sigport.org/5551},
author = { },
publisher = {IEEE SigPort},
title = {Skeleton Action Recognition Based on Singular Value Decomposition},
year = {2020} }
TY - EJOUR
T1 - Skeleton Action Recognition Based on Singular Value Decomposition
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5551
ER -
. (2020). Skeleton Action Recognition Based on Singular Value Decomposition. IEEE SigPort. http://sigport.org/5551
, 2020. Skeleton Action Recognition Based on Singular Value Decomposition. Available at: http://sigport.org/5551.
. (2020). "Skeleton Action Recognition Based on Singular Value Decomposition." Web.
1. . Skeleton Action Recognition Based on Singular Value Decomposition [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5551

Motion Blur Prior


Priors play an important role of regularizers in image deblurring algorithms. Image priors are frequently studied and many forms were proposed in the literature. Blur priors are considered less important and the most common forms are simple uniform distributions with domain constraints. We propose a more informative blur prior based on the notion of atomic norm which favors blurs composed of line segments and is suitable for motion blur. The prior is formulated as a linear program that can be inserted into any optimization task.

Paper Details

Authors:
F. Sroubek, J. Kotera
Submitted On:
4 November 2020 - 9:07am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP2020_prior.pdf

(11)

Subscribe

[1] F. Sroubek, J. Kotera, "Motion Blur Prior", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5534. Accessed: Dec. 02, 2020.
@article{5534-20,
url = {http://sigport.org/5534},
author = {F. Sroubek; J. Kotera },
publisher = {IEEE SigPort},
title = {Motion Blur Prior},
year = {2020} }
TY - EJOUR
T1 - Motion Blur Prior
AU - F. Sroubek; J. Kotera
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5534
ER -
F. Sroubek, J. Kotera. (2020). Motion Blur Prior. IEEE SigPort. http://sigport.org/5534
F. Sroubek, J. Kotera, 2020. Motion Blur Prior. Available at: http://sigport.org/5534.
F. Sroubek, J. Kotera. (2020). "Motion Blur Prior." Web.
1. F. Sroubek, J. Kotera. Motion Blur Prior [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5534

AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION


Texture is an indispensable property to develop many vision
based autonomous applications. Compared to colour, feature
dimension in a local texture descriptor is quite large as dense
texture features need to represent the distribution of pixel intensities
in the neighbourhood of each pixel. Large dimensional
features require additional time for further processing
that often restrict real-time applications. In this paper, a robust
local texture descriptor is enhanced by reducing feature

Paper Details

Authors:
Manzur Murshed, Shyh Wei Teng, Gour Karmakar
Submitted On:
3 November 2020 - 11:06pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

OralPresentationSlide_PaperID_2389.pptx

(7)

Subscribe

[1] Manzur Murshed, Shyh Wei Teng, Gour Karmakar, "AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5527. Accessed: Dec. 02, 2020.
@article{5527-20,
url = {http://sigport.org/5527},
author = {Manzur Murshed; Shyh Wei Teng; Gour Karmakar },
publisher = {IEEE SigPort},
title = {AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION},
year = {2020} }
TY - EJOUR
T1 - AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION
AU - Manzur Murshed; Shyh Wei Teng; Gour Karmakar
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5527
ER -
Manzur Murshed, Shyh Wei Teng, Gour Karmakar. (2020). AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION. IEEE SigPort. http://sigport.org/5527
Manzur Murshed, Shyh Wei Teng, Gour Karmakar, 2020. AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION. Available at: http://sigport.org/5527.
Manzur Murshed, Shyh Wei Teng, Gour Karmakar. (2020). "AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION." Web.
1. Manzur Murshed, Shyh Wei Teng, Gour Karmakar. AN ENHANCED LOCAL TEXTURE DESCRIPTOR FOR IMAGE SEGMENTATION [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5527

CSIOR:An Algorithm for Ordered Triangular Mesh Regularization


3D scanners generate irregularly distributed cloud of points in
most of the cases. Dealing with such data, often in the form of
triangular meshes, requires a pre-processing step to regularize
the triangle facets shape and size. In this paper, we propose
CSIOR, a novel mesh regularization technique which is capable
of producing quasi-equilateral triangles, and distinguished
by two novel features, namely, its intrinsic ordered aspect and
its preservation of the geometric texture of the surface (relief

Paper Details

Authors:
Submitted On:
3 November 2020 - 12:23am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Presentation.pdf

(48)

Subscribe

[1] , "CSIOR:An Algorithm for Ordered Triangular Mesh Regularization", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5502. Accessed: Dec. 02, 2020.
@article{5502-20,
url = {http://sigport.org/5502},
author = { },
publisher = {IEEE SigPort},
title = {CSIOR:An Algorithm for Ordered Triangular Mesh Regularization},
year = {2020} }
TY - EJOUR
T1 - CSIOR:An Algorithm for Ordered Triangular Mesh Regularization
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5502
ER -
. (2020). CSIOR:An Algorithm for Ordered Triangular Mesh Regularization. IEEE SigPort. http://sigport.org/5502
, 2020. CSIOR:An Algorithm for Ordered Triangular Mesh Regularization. Available at: http://sigport.org/5502.
. (2020). "CSIOR:An Algorithm for Ordered Triangular Mesh Regularization." Web.
1. . CSIOR:An Algorithm for Ordered Triangular Mesh Regularization [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5502

Spatial Keyframe Extraction of Mobile Videos for Efficient Object Detection at the Edge


Advances in federated learning and edge computing advocate for deep learning models to run at edge devices for video analysis. However, the captured video frame rate is too high to be processed at the edge in real-time with a typical model such as CNN. Any approach to consecutively feed frames to the model compromises both the quality (by missing important frames) and the efficiency (by processing redundantly similar frames) of analysis.

Paper Details

Authors:
George Constantinou, Cyrus Shahabi, Seon Ho Kim
Submitted On:
2 November 2020 - 4:52pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2020.pdf

(8)

Subscribe

[1] George Constantinou, Cyrus Shahabi, Seon Ho Kim, "Spatial Keyframe Extraction of Mobile Videos for Efficient Object Detection at the Edge", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5490. Accessed: Dec. 02, 2020.
@article{5490-20,
url = {http://sigport.org/5490},
author = {George Constantinou; Cyrus Shahabi; Seon Ho Kim },
publisher = {IEEE SigPort},
title = {Spatial Keyframe Extraction of Mobile Videos for Efficient Object Detection at the Edge},
year = {2020} }
TY - EJOUR
T1 - Spatial Keyframe Extraction of Mobile Videos for Efficient Object Detection at the Edge
AU - George Constantinou; Cyrus Shahabi; Seon Ho Kim
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5490
ER -
George Constantinou, Cyrus Shahabi, Seon Ho Kim. (2020). Spatial Keyframe Extraction of Mobile Videos for Efficient Object Detection at the Edge. IEEE SigPort. http://sigport.org/5490
George Constantinou, Cyrus Shahabi, Seon Ho Kim, 2020. Spatial Keyframe Extraction of Mobile Videos for Efficient Object Detection at the Edge. Available at: http://sigport.org/5490.
George Constantinou, Cyrus Shahabi, Seon Ho Kim. (2020). "Spatial Keyframe Extraction of Mobile Videos for Efficient Object Detection at the Edge." Web.
1. George Constantinou, Cyrus Shahabi, Seon Ho Kim. Spatial Keyframe Extraction of Mobile Videos for Efficient Object Detection at the Edge [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5490

PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance


Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations. Inspiration was usually taken from the human visual perceptual system and how the system processes different perturbations in order to replicate to what extent it determines our ability to judge image quality. While recent works have presented deep neural networks trained to predict human perceptual quality, very few borrow any intuitions from the human visual system.

Paper Details

Authors:
Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez
Submitted On:
2 November 2020 - 2:26pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP_2020_presentation.pdf

(9)

Subscribe

[1] Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez, "PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5483. Accessed: Dec. 02, 2020.
@article{5483-20,
url = {http://sigport.org/5483},
author = {Valero Laparra; Jesus Malo; Ryan McConville; Raul Santos-Rodriguez },
publisher = {IEEE SigPort},
title = {PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance},
year = {2020} }
TY - EJOUR
T1 - PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance
AU - Valero Laparra; Jesus Malo; Ryan McConville; Raul Santos-Rodriguez
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5483
ER -
Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez. (2020). PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance. IEEE SigPort. http://sigport.org/5483
Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez, 2020. PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance. Available at: http://sigport.org/5483.
Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez. (2020). "PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance." Web.
1. Valero Laparra, Jesus Malo, Ryan McConville, Raul Santos-Rodriguez. PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5483

Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary

Paper Details

Authors:
Submitted On:
2 November 2020 - 2:10pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Boundary of Distribution Support Generator (BDSG) Sample Generation on the Boundary.pdf

(25)

Subscribe

[1] , "Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5481. Accessed: Dec. 02, 2020.
@article{5481-20,
url = {http://sigport.org/5481},
author = { },
publisher = {IEEE SigPort},
title = {Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary},
year = {2020} }
TY - EJOUR
T1 - Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5481
ER -
. (2020). Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary. IEEE SigPort. http://sigport.org/5481
, 2020. Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary. Available at: http://sigport.org/5481.
. (2020). "Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary." Web.
1. . Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5481

Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]

Paper Details

Authors:
Adrián Martín, Gloria Haro, Coloma Ballester
Submitted On:
2 November 2020 - 12:17pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

SlidesICIP.pdf

(10)

Subscribe

[1] Adrián Martín, Gloria Haro, Coloma Ballester, "Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5477. Accessed: Dec. 02, 2020.
@article{5477-20,
url = {http://sigport.org/5477},
author = {Adrián Martín; Gloria Haro; Coloma Ballester },
publisher = {IEEE SigPort},
title = {Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]},
year = {2020} }
TY - EJOUR
T1 - Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]
AU - Adrián Martín; Gloria Haro; Coloma Ballester
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5477
ER -
Adrián Martín, Gloria Haro, Coloma Ballester. (2020). Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]. IEEE SigPort. http://sigport.org/5477
Adrián Martín, Gloria Haro, Coloma Ballester, 2020. Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]. Available at: http://sigport.org/5477.
Adrián Martín, Gloria Haro, Coloma Ballester. (2020). "Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides]." Web.
1. Adrián Martín, Gloria Haro, Coloma Ballester. Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [Slides] [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5477

Pages