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

Image/Video Processing

3D reconstruction using single-photon Lidar data: exploiting the widths of the returns


Single-photon light detection and ranging (Lidar) data can be used to capture depth and intensity profiles of a 3D scene. In a general setting, the scenes can have an unknown number of surfaces per pixel (semi-transparent surfaces or outdoor measurements), high background noise (strong ambient illumination), can be acquired by systems with a broad instrumental response (non-parallel laser beam with respect to the target surface) and with possibly high attenuating media (underwater conditions).

Paper Details

Authors:
Submitted On:
9 May 2019 - 7:08am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP19.pptx

(11)

Subscribe

[1] , "3D reconstruction using single-photon Lidar data: exploiting the widths of the returns", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4189. Accessed: Jul. 20, 2019.
@article{4189-19,
url = {http://sigport.org/4189},
author = { },
publisher = {IEEE SigPort},
title = {3D reconstruction using single-photon Lidar data: exploiting the widths of the returns},
year = {2019} }
TY - EJOUR
T1 - 3D reconstruction using single-photon Lidar data: exploiting the widths of the returns
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4189
ER -
. (2019). 3D reconstruction using single-photon Lidar data: exploiting the widths of the returns. IEEE SigPort. http://sigport.org/4189
, 2019. 3D reconstruction using single-photon Lidar data: exploiting the widths of the returns. Available at: http://sigport.org/4189.
. (2019). "3D reconstruction using single-photon Lidar data: exploiting the widths of the returns." Web.
1. . 3D reconstruction using single-photon Lidar data: exploiting the widths of the returns [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4189

Deep Graph Regularized Learning for Binary Classification

Paper Details

Authors:
Minxiang Ye, Vladimir Stankovic, Lina Stankovic, Gene Cheung
Submitted On:
9 May 2019 - 6:08am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_SENSIBLE.pdf

(12)

Subscribe

[1] Minxiang Ye, Vladimir Stankovic, Lina Stankovic, Gene Cheung, "Deep Graph Regularized Learning for Binary Classification", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4182. Accessed: Jul. 20, 2019.
@article{4182-19,
url = {http://sigport.org/4182},
author = {Minxiang Ye; Vladimir Stankovic; Lina Stankovic; Gene Cheung },
publisher = {IEEE SigPort},
title = {Deep Graph Regularized Learning for Binary Classification},
year = {2019} }
TY - EJOUR
T1 - Deep Graph Regularized Learning for Binary Classification
AU - Minxiang Ye; Vladimir Stankovic; Lina Stankovic; Gene Cheung
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4182
ER -
Minxiang Ye, Vladimir Stankovic, Lina Stankovic, Gene Cheung. (2019). Deep Graph Regularized Learning for Binary Classification. IEEE SigPort. http://sigport.org/4182
Minxiang Ye, Vladimir Stankovic, Lina Stankovic, Gene Cheung, 2019. Deep Graph Regularized Learning for Binary Classification. Available at: http://sigport.org/4182.
Minxiang Ye, Vladimir Stankovic, Lina Stankovic, Gene Cheung. (2019). "Deep Graph Regularized Learning for Binary Classification." Web.
1. Minxiang Ye, Vladimir Stankovic, Lina Stankovic, Gene Cheung. Deep Graph Regularized Learning for Binary Classification [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4182

VISUAL RELATIONSHIP RECOGNITION VIA LANGUAGE AND POSITION GUIDED ATTENTION


Visual relationship recognition, as a challenging task used to distinguish the interactions between object pairs, has received much attention recently. Considering the fact that most visual relationships are semantic concepts defined by human beings, there are many human knowledge, or priors, hidden in them, which haven’t been fully exploited by existing methods.

Paper Details

Authors:
Hao Zhou,Chuanping Hu,Chongyang Zhang,Shengyang Shen
Submitted On:
9 May 2019 - 6:05am
Short Link:
Type:
Event:

Document Files

poster_icassp_1741.pdf

(15)

Subscribe

[1] Hao Zhou,Chuanping Hu,Chongyang Zhang,Shengyang Shen, "VISUAL RELATIONSHIP RECOGNITION VIA LANGUAGE AND POSITION GUIDED ATTENTION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4179. Accessed: Jul. 20, 2019.
@article{4179-19,
url = {http://sigport.org/4179},
author = {Hao Zhou;Chuanping Hu;Chongyang Zhang;Shengyang Shen },
publisher = {IEEE SigPort},
title = {VISUAL RELATIONSHIP RECOGNITION VIA LANGUAGE AND POSITION GUIDED ATTENTION},
year = {2019} }
TY - EJOUR
T1 - VISUAL RELATIONSHIP RECOGNITION VIA LANGUAGE AND POSITION GUIDED ATTENTION
AU - Hao Zhou;Chuanping Hu;Chongyang Zhang;Shengyang Shen
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4179
ER -
Hao Zhou,Chuanping Hu,Chongyang Zhang,Shengyang Shen. (2019). VISUAL RELATIONSHIP RECOGNITION VIA LANGUAGE AND POSITION GUIDED ATTENTION. IEEE SigPort. http://sigport.org/4179
Hao Zhou,Chuanping Hu,Chongyang Zhang,Shengyang Shen, 2019. VISUAL RELATIONSHIP RECOGNITION VIA LANGUAGE AND POSITION GUIDED ATTENTION. Available at: http://sigport.org/4179.
Hao Zhou,Chuanping Hu,Chongyang Zhang,Shengyang Shen. (2019). "VISUAL RELATIONSHIP RECOGNITION VIA LANGUAGE AND POSITION GUIDED ATTENTION." Web.
1. Hao Zhou,Chuanping Hu,Chongyang Zhang,Shengyang Shen. VISUAL RELATIONSHIP RECOGNITION VIA LANGUAGE AND POSITION GUIDED ATTENTION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4179

Interactive Subjective Study on Picture-level Just Noticeable Difference of Compressed Stereoscopic Images


The Just Noticeable Difference (JND) reveals the minimum distortion that the Human Visual System (HVS) can perceive. Traditional studies on JND mainly focus on background luminance adaptation and contrast masking. However, the HVS does not perceive visual content based on individual pixels or blocks, but on the entire image. In this work, we conduct an interactive subjective visual quality study on the Picture-level JND (PJND) of compressed stereo images. The study, which involves 48 subjects and 10 stereoscopic images compressed with H.265 intra coding and JPEG2000, includes two parts.

Paper Details

Authors:
Chunling Fan, Yun Zhang, Raouf Hamzaoui, Qingshan Jiang
Submitted On:
9 May 2019 - 9:51pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster_3509.pdf

(17)

Subscribe

[1] Chunling Fan, Yun Zhang, Raouf Hamzaoui, Qingshan Jiang, "Interactive Subjective Study on Picture-level Just Noticeable Difference of Compressed Stereoscopic Images", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4173. Accessed: Jul. 20, 2019.
@article{4173-19,
url = {http://sigport.org/4173},
author = {Chunling Fan; Yun Zhang; Raouf Hamzaoui; Qingshan Jiang },
publisher = {IEEE SigPort},
title = {Interactive Subjective Study on Picture-level Just Noticeable Difference of Compressed Stereoscopic Images},
year = {2019} }
TY - EJOUR
T1 - Interactive Subjective Study on Picture-level Just Noticeable Difference of Compressed Stereoscopic Images
AU - Chunling Fan; Yun Zhang; Raouf Hamzaoui; Qingshan Jiang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4173
ER -
Chunling Fan, Yun Zhang, Raouf Hamzaoui, Qingshan Jiang. (2019). Interactive Subjective Study on Picture-level Just Noticeable Difference of Compressed Stereoscopic Images. IEEE SigPort. http://sigport.org/4173
Chunling Fan, Yun Zhang, Raouf Hamzaoui, Qingshan Jiang, 2019. Interactive Subjective Study on Picture-level Just Noticeable Difference of Compressed Stereoscopic Images. Available at: http://sigport.org/4173.
Chunling Fan, Yun Zhang, Raouf Hamzaoui, Qingshan Jiang. (2019). "Interactive Subjective Study on Picture-level Just Noticeable Difference of Compressed Stereoscopic Images." Web.
1. Chunling Fan, Yun Zhang, Raouf Hamzaoui, Qingshan Jiang. Interactive Subjective Study on Picture-level Just Noticeable Difference of Compressed Stereoscopic Images [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4173

OPTIMIZED COLOR-GUIDED FILTER FOR DEPTH IMAGE DENOISING


Color Guided Depth image denoising often suffers from the texture coping from the color image as well as the blurry effect at the depth discontinuities. Motivated by this, we propose an optimized color-guided filter for depth image denoising from different types of noises. This is a new framework that helps to mitigate the texture coping and enhance the depth discontinuities, especially in heavy noises. This framework consists of two parts namely depth driven color flattening model and patch synthesis-based Markov random field model.

Paper Details

Authors:
Mostafa M. Ibrahim, Qiong Liu
Submitted On:
9 May 2019 - 1:11am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_Poster.pdf

(196)

Subscribe

[1] Mostafa M. Ibrahim, Qiong Liu, "OPTIMIZED COLOR-GUIDED FILTER FOR DEPTH IMAGE DENOISING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4149. Accessed: Jul. 20, 2019.
@article{4149-19,
url = {http://sigport.org/4149},
author = {Mostafa M. Ibrahim; Qiong Liu },
publisher = {IEEE SigPort},
title = {OPTIMIZED COLOR-GUIDED FILTER FOR DEPTH IMAGE DENOISING},
year = {2019} }
TY - EJOUR
T1 - OPTIMIZED COLOR-GUIDED FILTER FOR DEPTH IMAGE DENOISING
AU - Mostafa M. Ibrahim; Qiong Liu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4149
ER -
Mostafa M. Ibrahim, Qiong Liu. (2019). OPTIMIZED COLOR-GUIDED FILTER FOR DEPTH IMAGE DENOISING. IEEE SigPort. http://sigport.org/4149
Mostafa M. Ibrahim, Qiong Liu, 2019. OPTIMIZED COLOR-GUIDED FILTER FOR DEPTH IMAGE DENOISING. Available at: http://sigport.org/4149.
Mostafa M. Ibrahim, Qiong Liu. (2019). "OPTIMIZED COLOR-GUIDED FILTER FOR DEPTH IMAGE DENOISING." Web.
1. Mostafa M. Ibrahim, Qiong Liu. OPTIMIZED COLOR-GUIDED FILTER FOR DEPTH IMAGE DENOISING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4149

Video-Based, Occlusion-Robust Multi-View Stereo Using Inner-Boundary Depths of Textureless Areas


Occlusions and poor textures are two main problems in multi-view stereo reconstruction. This paper presents a video-based solution to address both challenges in depth estimation. We focus on reconstructing accurate inner boundaries of visible textureless areas, particularly for occluded background, by leveraging the reliable depths of object edges. This is done by efficiently respecting two local cues with complementary advantages, i.e. smoothness and density of recovered surfaces.

Paper Details

Authors:
Jian Wei, Shigang Wang, Yan Zhao
Submitted On:
8 May 2019 - 10:48pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP2019.pdf

(10)

Subscribe

[1] Jian Wei, Shigang Wang, Yan Zhao, "Video-Based, Occlusion-Robust Multi-View Stereo Using Inner-Boundary Depths of Textureless Areas", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4143. Accessed: Jul. 20, 2019.
@article{4143-19,
url = {http://sigport.org/4143},
author = {Jian Wei; Shigang Wang; Yan Zhao },
publisher = {IEEE SigPort},
title = {Video-Based, Occlusion-Robust Multi-View Stereo Using Inner-Boundary Depths of Textureless Areas},
year = {2019} }
TY - EJOUR
T1 - Video-Based, Occlusion-Robust Multi-View Stereo Using Inner-Boundary Depths of Textureless Areas
AU - Jian Wei; Shigang Wang; Yan Zhao
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4143
ER -
Jian Wei, Shigang Wang, Yan Zhao. (2019). Video-Based, Occlusion-Robust Multi-View Stereo Using Inner-Boundary Depths of Textureless Areas. IEEE SigPort. http://sigport.org/4143
Jian Wei, Shigang Wang, Yan Zhao, 2019. Video-Based, Occlusion-Robust Multi-View Stereo Using Inner-Boundary Depths of Textureless Areas. Available at: http://sigport.org/4143.
Jian Wei, Shigang Wang, Yan Zhao. (2019). "Video-Based, Occlusion-Robust Multi-View Stereo Using Inner-Boundary Depths of Textureless Areas." Web.
1. Jian Wei, Shigang Wang, Yan Zhao. Video-Based, Occlusion-Robust Multi-View Stereo Using Inner-Boundary Depths of Textureless Areas [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4143

Transform Domain based Medical Image Super-Resolution via Deep Multi-scale Network


This paper proposes a new medical image super-resolution (SR) network, namely deep multi-scale network (DMSN), in the uniform discrete curvelet transform (UDCT) domain. DMSN is made up of a set of cascaded multi-scale fushion (MSF) blocks. In each MSF block, we use convolution kernels of different sizes to adaptively detect the local multiscale feature, and then local residual learning (LRL) is used to learn effective feature from preceding MSF block and current multi-scale features.

Paper Details

Authors:
Simiao Wang; Bin Ma; Jian Li; Xiangjun Dong; Zhiqiu Xia
Submitted On:
8 May 2019 - 9:28pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster.pdf

(19)

Subscribe

[1] Simiao Wang; Bin Ma; Jian Li; Xiangjun Dong; Zhiqiu Xia, "Transform Domain based Medical Image Super-Resolution via Deep Multi-scale Network", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4138. Accessed: Jul. 20, 2019.
@article{4138-19,
url = {http://sigport.org/4138},
author = {Simiao Wang; Bin Ma; Jian Li; Xiangjun Dong; Zhiqiu Xia },
publisher = {IEEE SigPort},
title = {Transform Domain based Medical Image Super-Resolution via Deep Multi-scale Network},
year = {2019} }
TY - EJOUR
T1 - Transform Domain based Medical Image Super-Resolution via Deep Multi-scale Network
AU - Simiao Wang; Bin Ma; Jian Li; Xiangjun Dong; Zhiqiu Xia
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4138
ER -
Simiao Wang; Bin Ma; Jian Li; Xiangjun Dong; Zhiqiu Xia. (2019). Transform Domain based Medical Image Super-Resolution via Deep Multi-scale Network. IEEE SigPort. http://sigport.org/4138
Simiao Wang; Bin Ma; Jian Li; Xiangjun Dong; Zhiqiu Xia, 2019. Transform Domain based Medical Image Super-Resolution via Deep Multi-scale Network. Available at: http://sigport.org/4138.
Simiao Wang; Bin Ma; Jian Li; Xiangjun Dong; Zhiqiu Xia. (2019). "Transform Domain based Medical Image Super-Resolution via Deep Multi-scale Network." Web.
1. Simiao Wang; Bin Ma; Jian Li; Xiangjun Dong; Zhiqiu Xia. Transform Domain based Medical Image Super-Resolution via Deep Multi-scale Network [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4138

An Algorithm Unrolling Approach to Deep Image Deblurring


While neural networks have achieved vastly enhanced performance over traditional iterative methods in many cases, they are generally empirically designed and the underlying structures are difficult to interpret. The algorithm unrolling approach has helped connect iterative algorithms to neural network architectures. However, such connections have not been made yet for blind image deblurring. In this paper, we propose a neural network architecture that advances this idea.

Paper Details

Authors:
Yuelong Li, Vishal Monga, Yonina C. Eldar
Submitted On:
8 May 2019 - 4:34pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_2019.pdf

(18)

Keywords

Additional Categories

Subscribe

[1] Yuelong Li, Vishal Monga, Yonina C. Eldar, "An Algorithm Unrolling Approach to Deep Image Deblurring", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4133. Accessed: Jul. 20, 2019.
@article{4133-19,
url = {http://sigport.org/4133},
author = {Yuelong Li; Vishal Monga; Yonina C. Eldar },
publisher = {IEEE SigPort},
title = {An Algorithm Unrolling Approach to Deep Image Deblurring},
year = {2019} }
TY - EJOUR
T1 - An Algorithm Unrolling Approach to Deep Image Deblurring
AU - Yuelong Li; Vishal Monga; Yonina C. Eldar
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4133
ER -
Yuelong Li, Vishal Monga, Yonina C. Eldar. (2019). An Algorithm Unrolling Approach to Deep Image Deblurring. IEEE SigPort. http://sigport.org/4133
Yuelong Li, Vishal Monga, Yonina C. Eldar, 2019. An Algorithm Unrolling Approach to Deep Image Deblurring. Available at: http://sigport.org/4133.
Yuelong Li, Vishal Monga, Yonina C. Eldar. (2019). "An Algorithm Unrolling Approach to Deep Image Deblurring." Web.
1. Yuelong Li, Vishal Monga, Yonina C. Eldar. An Algorithm Unrolling Approach to Deep Image Deblurring [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4133

3D VISUAL SPEECH ANIMATION USING 2D VIDEOS


In visual speech animation, lip motion accuracy is of paramount importance for speech intelligibility, especially for the hard of hearing or foreign language learners. We present an approach for visual speech animation that uses tracked lip motion in front-view 2D videos of a real speaker to drive the lip motion of a synthetic 3D head. This makes use of a 3D morphable model (3DMM), built using 3D synthetic head poses, with corresponding landmarks identified in the 2D videos and the 3DMM.

Paper Details

Authors:
Rabab Algadhy , Yoshihiko Gotoh , Steve Maddock
Submitted On:
8 May 2019 - 8:26am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

3D Visual Speech Animation Using 2D Videos.pdf

(12)

Subscribe

[1] Rabab Algadhy , Yoshihiko Gotoh , Steve Maddock, "3D VISUAL SPEECH ANIMATION USING 2D VIDEOS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4084. Accessed: Jul. 20, 2019.
@article{4084-19,
url = {http://sigport.org/4084},
author = {Rabab Algadhy ; Yoshihiko Gotoh ; Steve Maddock },
publisher = {IEEE SigPort},
title = {3D VISUAL SPEECH ANIMATION USING 2D VIDEOS},
year = {2019} }
TY - EJOUR
T1 - 3D VISUAL SPEECH ANIMATION USING 2D VIDEOS
AU - Rabab Algadhy ; Yoshihiko Gotoh ; Steve Maddock
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4084
ER -
Rabab Algadhy , Yoshihiko Gotoh , Steve Maddock. (2019). 3D VISUAL SPEECH ANIMATION USING 2D VIDEOS. IEEE SigPort. http://sigport.org/4084
Rabab Algadhy , Yoshihiko Gotoh , Steve Maddock, 2019. 3D VISUAL SPEECH ANIMATION USING 2D VIDEOS. Available at: http://sigport.org/4084.
Rabab Algadhy , Yoshihiko Gotoh , Steve Maddock. (2019). "3D VISUAL SPEECH ANIMATION USING 2D VIDEOS." Web.
1. Rabab Algadhy , Yoshihiko Gotoh , Steve Maddock. 3D VISUAL SPEECH ANIMATION USING 2D VIDEOS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4084

View-Invariant Action Recognition From RGB Data via 3D Pose Estimation


In this paper, we propose a novel view-invariant action recognition method using a single monocular RGB camera. View-invariance remains a very challenging topic in 2D action recognition due to the lack of 3D information in RGB images. Most successful approaches make use of the concept of knowledge transfer by projecting 3D synthetic data to multiple viewpoints. Instead of relying on knowledge transfer, we propose to augment the RGB data by a third dimension by means of 3D skeleton estimation from 2D images using a CNN-based pose estimator.

Paper Details

Authors:
Enjie Ghorbel, Konstantinos Papadopoulos, Girum G. Demisse, Djamila Aouada, Björn Ottersten
Submitted On:
8 May 2019 - 7:19am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP_Renato_final.pdf

(13)

Subscribe

[1] Enjie Ghorbel, Konstantinos Papadopoulos, Girum G. Demisse, Djamila Aouada, Björn Ottersten, "View-Invariant Action Recognition From RGB Data via 3D Pose Estimation", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4073. Accessed: Jul. 20, 2019.
@article{4073-19,
url = {http://sigport.org/4073},
author = {Enjie Ghorbel; Konstantinos Papadopoulos; Girum G. Demisse; Djamila Aouada; Björn Ottersten },
publisher = {IEEE SigPort},
title = {View-Invariant Action Recognition From RGB Data via 3D Pose Estimation},
year = {2019} }
TY - EJOUR
T1 - View-Invariant Action Recognition From RGB Data via 3D Pose Estimation
AU - Enjie Ghorbel; Konstantinos Papadopoulos; Girum G. Demisse; Djamila Aouada; Björn Ottersten
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4073
ER -
Enjie Ghorbel, Konstantinos Papadopoulos, Girum G. Demisse, Djamila Aouada, Björn Ottersten. (2019). View-Invariant Action Recognition From RGB Data via 3D Pose Estimation. IEEE SigPort. http://sigport.org/4073
Enjie Ghorbel, Konstantinos Papadopoulos, Girum G. Demisse, Djamila Aouada, Björn Ottersten, 2019. View-Invariant Action Recognition From RGB Data via 3D Pose Estimation. Available at: http://sigport.org/4073.
Enjie Ghorbel, Konstantinos Papadopoulos, Girum G. Demisse, Djamila Aouada, Björn Ottersten. (2019). "View-Invariant Action Recognition From RGB Data via 3D Pose Estimation." Web.
1. Enjie Ghorbel, Konstantinos Papadopoulos, Girum G. Demisse, Djamila Aouada, Björn Ottersten. View-Invariant Action Recognition From RGB Data via 3D Pose Estimation [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4073

Pages