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

Image/Video Coding

Blocksize-QP dependent intra interpolation filters


Intra interpolation filters for intra angular prediction play an important role in the coding performance. In the intra angular prediction of VVC, which is being standardized by the joint video coding expert team (JVET), block-size based switchable interpolation filters between 4-tap cubic and Gaussian interpolation filters is being studied. Although the two filters have different frequency characteristics, block size-based criteria are insufficient to represent the reference sample characteristics.

Paper Details

Authors:
Yoshitaka Kidani, Kei Kawamura, Kyohei Unno, Sei Naito
Submitted On:
20 September 2019 - 5:12am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019_P2450.pdf

(2)

Subscribe

[1] Yoshitaka Kidani, Kei Kawamura, Kyohei Unno, Sei Naito, "Blocksize-QP dependent intra interpolation filters", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4770. Accessed: Sep. 20, 2019.
@article{4770-19,
url = {http://sigport.org/4770},
author = {Yoshitaka Kidani; Kei Kawamura; Kyohei Unno; Sei Naito },
publisher = {IEEE SigPort},
title = {Blocksize-QP dependent intra interpolation filters},
year = {2019} }
TY - EJOUR
T1 - Blocksize-QP dependent intra interpolation filters
AU - Yoshitaka Kidani; Kei Kawamura; Kyohei Unno; Sei Naito
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4770
ER -
Yoshitaka Kidani, Kei Kawamura, Kyohei Unno, Sei Naito. (2019). Blocksize-QP dependent intra interpolation filters. IEEE SigPort. http://sigport.org/4770
Yoshitaka Kidani, Kei Kawamura, Kyohei Unno, Sei Naito, 2019. Blocksize-QP dependent intra interpolation filters. Available at: http://sigport.org/4770.
Yoshitaka Kidani, Kei Kawamura, Kyohei Unno, Sei Naito. (2019). "Blocksize-QP dependent intra interpolation filters." Web.
1. Yoshitaka Kidani, Kei Kawamura, Kyohei Unno, Sei Naito. Blocksize-QP dependent intra interpolation filters [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4770

Image Pre-Transformation for Recognition-Aware Image Compression

Paper Details

Authors:
Motohiro Takagi, Kazuya Hayase, Takayuki Onishi, Atsushi Shimizu
Submitted On:
20 September 2019 - 5:14am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

ICIP2019_suzuki_emb.pdf

(1)

Subscribe

[1] Motohiro Takagi, Kazuya Hayase, Takayuki Onishi, Atsushi Shimizu, "Image Pre-Transformation for Recognition-Aware Image Compression", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4768. Accessed: Sep. 20, 2019.
@article{4768-19,
url = {http://sigport.org/4768},
author = {Motohiro Takagi; Kazuya Hayase; Takayuki Onishi; Atsushi Shimizu },
publisher = {IEEE SigPort},
title = {Image Pre-Transformation for Recognition-Aware Image Compression},
year = {2019} }
TY - EJOUR
T1 - Image Pre-Transformation for Recognition-Aware Image Compression
AU - Motohiro Takagi; Kazuya Hayase; Takayuki Onishi; Atsushi Shimizu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4768
ER -
Motohiro Takagi, Kazuya Hayase, Takayuki Onishi, Atsushi Shimizu. (2019). Image Pre-Transformation for Recognition-Aware Image Compression. IEEE SigPort. http://sigport.org/4768
Motohiro Takagi, Kazuya Hayase, Takayuki Onishi, Atsushi Shimizu, 2019. Image Pre-Transformation for Recognition-Aware Image Compression. Available at: http://sigport.org/4768.
Motohiro Takagi, Kazuya Hayase, Takayuki Onishi, Atsushi Shimizu. (2019). "Image Pre-Transformation for Recognition-Aware Image Compression." Web.
1. Motohiro Takagi, Kazuya Hayase, Takayuki Onishi, Atsushi Shimizu. Image Pre-Transformation for Recognition-Aware Image Compression [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4768

Two-layer Near-lossless HDR Coding with Backward Compatibility to JPEG

Paper Details

Authors:
Hiroyuki KOBAYASHI, Osamu WATANABE, Hitoshi KIYA
Submitted On:
19 September 2019 - 3:31am
Short Link:
Type:
Event:
Presenter's Name:

Document Files

icip2019_poster.pdf

(9)

Subscribe

[1] Hiroyuki KOBAYASHI, Osamu WATANABE, Hitoshi KIYA, "Two-layer Near-lossless HDR Coding with Backward Compatibility to JPEG", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4710. Accessed: Sep. 20, 2019.
@article{4710-19,
url = {http://sigport.org/4710},
author = {Hiroyuki KOBAYASHI; Osamu WATANABE; Hitoshi KIYA },
publisher = {IEEE SigPort},
title = {Two-layer Near-lossless HDR Coding with Backward Compatibility to JPEG},
year = {2019} }
TY - EJOUR
T1 - Two-layer Near-lossless HDR Coding with Backward Compatibility to JPEG
AU - Hiroyuki KOBAYASHI; Osamu WATANABE; Hitoshi KIYA
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4710
ER -
Hiroyuki KOBAYASHI, Osamu WATANABE, Hitoshi KIYA. (2019). Two-layer Near-lossless HDR Coding with Backward Compatibility to JPEG. IEEE SigPort. http://sigport.org/4710
Hiroyuki KOBAYASHI, Osamu WATANABE, Hitoshi KIYA, 2019. Two-layer Near-lossless HDR Coding with Backward Compatibility to JPEG. Available at: http://sigport.org/4710.
Hiroyuki KOBAYASHI, Osamu WATANABE, Hitoshi KIYA. (2019). "Two-layer Near-lossless HDR Coding with Backward Compatibility to JPEG." Web.
1. Hiroyuki KOBAYASHI, Osamu WATANABE, Hitoshi KIYA. Two-layer Near-lossless HDR Coding with Backward Compatibility to JPEG [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4710

RATE-DISTORTION OPTIMIZED TREE-STRUCTURED POINT-LATTICE VECTOR QUANTIZATION FOR COMPRESSION OF 3D POINT CLOUDS GEOMETRY


This paper deals with the current trends of new compression methods for 3D point cloud contents required to ensure efficient transmission and storage.
The representation of 3D point clouds geometry remains a challenging problem, since this signal is unstructured.
In this paper, we introduce a new hierarchical geometry representation based on adaptive Tree-Structured Point-Lattice Vector Quantization (TSPLVQ).
This representation enables hierarchically structured 3D content that improves the compression performance for static point clouds.

Paper Details

Authors:
Amira Filali, Vincent Ricordel, Nicolas Normand, Wassim Hamidouche
Submitted On:
18 September 2019 - 11:27am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

eposter_icip_VR.pdf

(2)

Subscribe

[1] Amira Filali, Vincent Ricordel, Nicolas Normand, Wassim Hamidouche, "RATE-DISTORTION OPTIMIZED TREE-STRUCTURED POINT-LATTICE VECTOR QUANTIZATION FOR COMPRESSION OF 3D POINT CLOUDS GEOMETRY", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4684. Accessed: Sep. 20, 2019.
@article{4684-19,
url = {http://sigport.org/4684},
author = {Amira Filali; Vincent Ricordel; Nicolas Normand; Wassim Hamidouche },
publisher = {IEEE SigPort},
title = {RATE-DISTORTION OPTIMIZED TREE-STRUCTURED POINT-LATTICE VECTOR QUANTIZATION FOR COMPRESSION OF 3D POINT CLOUDS GEOMETRY},
year = {2019} }
TY - EJOUR
T1 - RATE-DISTORTION OPTIMIZED TREE-STRUCTURED POINT-LATTICE VECTOR QUANTIZATION FOR COMPRESSION OF 3D POINT CLOUDS GEOMETRY
AU - Amira Filali; Vincent Ricordel; Nicolas Normand; Wassim Hamidouche
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4684
ER -
Amira Filali, Vincent Ricordel, Nicolas Normand, Wassim Hamidouche. (2019). RATE-DISTORTION OPTIMIZED TREE-STRUCTURED POINT-LATTICE VECTOR QUANTIZATION FOR COMPRESSION OF 3D POINT CLOUDS GEOMETRY. IEEE SigPort. http://sigport.org/4684
Amira Filali, Vincent Ricordel, Nicolas Normand, Wassim Hamidouche, 2019. RATE-DISTORTION OPTIMIZED TREE-STRUCTURED POINT-LATTICE VECTOR QUANTIZATION FOR COMPRESSION OF 3D POINT CLOUDS GEOMETRY. Available at: http://sigport.org/4684.
Amira Filali, Vincent Ricordel, Nicolas Normand, Wassim Hamidouche. (2019). "RATE-DISTORTION OPTIMIZED TREE-STRUCTURED POINT-LATTICE VECTOR QUANTIZATION FOR COMPRESSION OF 3D POINT CLOUDS GEOMETRY." Web.
1. Amira Filali, Vincent Ricordel, Nicolas Normand, Wassim Hamidouche. RATE-DISTORTION OPTIMIZED TREE-STRUCTURED POINT-LATTICE VECTOR QUANTIZATION FOR COMPRESSION OF 3D POINT CLOUDS GEOMETRY [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4684

AN AFFINE-LINEAR INTRA PREDICTION WITH COMPLEXITY CONSTRAINTS


This paper presents a novel method for a data-driven training of
affine-linear predictors which perform intra prediction in state-ofthe-
art video coding. The main aspect of our training design is the
use of subband decomposition of both the input and the output of the
prediction. Due to this architecture, the same set of predictors can be
shared across different block shapes leading to a very limited memory
requirement. Also, the computational complexity of the resulting
predictors can be limited such that it does not exceed the complexity

Paper Details

Authors:
Jonathan Pfaff, Björn Stallenberger, Philipp Helle, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
Submitted On:
18 September 2019 - 10:19am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

lwip_poster.pdf

(3)

Subscribe

[1] Jonathan Pfaff, Björn Stallenberger, Philipp Helle, Heiko Schwarz, Detlev Marpe, Thomas Wiegand, "AN AFFINE-LINEAR INTRA PREDICTION WITH COMPLEXITY CONSTRAINTS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4679. Accessed: Sep. 20, 2019.
@article{4679-19,
url = {http://sigport.org/4679},
author = {Jonathan Pfaff; Björn Stallenberger; Philipp Helle; Heiko Schwarz; Detlev Marpe; Thomas Wiegand },
publisher = {IEEE SigPort},
title = {AN AFFINE-LINEAR INTRA PREDICTION WITH COMPLEXITY CONSTRAINTS},
year = {2019} }
TY - EJOUR
T1 - AN AFFINE-LINEAR INTRA PREDICTION WITH COMPLEXITY CONSTRAINTS
AU - Jonathan Pfaff; Björn Stallenberger; Philipp Helle; Heiko Schwarz; Detlev Marpe; Thomas Wiegand
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4679
ER -
Jonathan Pfaff, Björn Stallenberger, Philipp Helle, Heiko Schwarz, Detlev Marpe, Thomas Wiegand. (2019). AN AFFINE-LINEAR INTRA PREDICTION WITH COMPLEXITY CONSTRAINTS. IEEE SigPort. http://sigport.org/4679
Jonathan Pfaff, Björn Stallenberger, Philipp Helle, Heiko Schwarz, Detlev Marpe, Thomas Wiegand, 2019. AN AFFINE-LINEAR INTRA PREDICTION WITH COMPLEXITY CONSTRAINTS. Available at: http://sigport.org/4679.
Jonathan Pfaff, Björn Stallenberger, Philipp Helle, Heiko Schwarz, Detlev Marpe, Thomas Wiegand. (2019). "AN AFFINE-LINEAR INTRA PREDICTION WITH COMPLEXITY CONSTRAINTS." Web.
1. Jonathan Pfaff, Björn Stallenberger, Philipp Helle, Heiko Schwarz, Detlev Marpe, Thomas Wiegand. AN AFFINE-LINEAR INTRA PREDICTION WITH COMPLEXITY CONSTRAINTS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4679

EFFICIENT CODING OF 360° VIDEOS EXPLOITING INACTIVE REGIONS IN PROJECTION FORMATS


This paper presents an efficient method for encoding common projection formats in 360◦ video coding, in which we exploit inactive regions. These regions are ignored in the reconstruction of the equirectangular format or the viewport in virtual reality applications. As the content of these pixels is irrelevant, we neglect the corresponding pixel values in ratedistortion optimization, residual transformation, as well as inloop filtering and achieve bitrate savings of up to 10%.

Paper Details

Authors:
Christian Herglotz, Mohammadreza Jamali, Stéphane Coulombe, Carlos Vazquez, Ahmad Vakili
Submitted On:
18 September 2019 - 8:32am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster

(1)

Subscribe

[1] Christian Herglotz, Mohammadreza Jamali, Stéphane Coulombe, Carlos Vazquez, Ahmad Vakili, "EFFICIENT CODING OF 360° VIDEOS EXPLOITING INACTIVE REGIONS IN PROJECTION FORMATS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4674. Accessed: Sep. 20, 2019.
@article{4674-19,
url = {http://sigport.org/4674},
author = {Christian Herglotz; Mohammadreza Jamali; Stéphane Coulombe; Carlos Vazquez; Ahmad Vakili },
publisher = {IEEE SigPort},
title = {EFFICIENT CODING OF 360° VIDEOS EXPLOITING INACTIVE REGIONS IN PROJECTION FORMATS},
year = {2019} }
TY - EJOUR
T1 - EFFICIENT CODING OF 360° VIDEOS EXPLOITING INACTIVE REGIONS IN PROJECTION FORMATS
AU - Christian Herglotz; Mohammadreza Jamali; Stéphane Coulombe; Carlos Vazquez; Ahmad Vakili
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4674
ER -
Christian Herglotz, Mohammadreza Jamali, Stéphane Coulombe, Carlos Vazquez, Ahmad Vakili. (2019). EFFICIENT CODING OF 360° VIDEOS EXPLOITING INACTIVE REGIONS IN PROJECTION FORMATS. IEEE SigPort. http://sigport.org/4674
Christian Herglotz, Mohammadreza Jamali, Stéphane Coulombe, Carlos Vazquez, Ahmad Vakili, 2019. EFFICIENT CODING OF 360° VIDEOS EXPLOITING INACTIVE REGIONS IN PROJECTION FORMATS. Available at: http://sigport.org/4674.
Christian Herglotz, Mohammadreza Jamali, Stéphane Coulombe, Carlos Vazquez, Ahmad Vakili. (2019). "EFFICIENT CODING OF 360° VIDEOS EXPLOITING INACTIVE REGIONS IN PROJECTION FORMATS." Web.
1. Christian Herglotz, Mohammadreza Jamali, Stéphane Coulombe, Carlos Vazquez, Ahmad Vakili. EFFICIENT CODING OF 360° VIDEOS EXPLOITING INACTIVE REGIONS IN PROJECTION FORMATS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4674

Real-Time HDR Video Tone Mapping Using High Efficiency Video Coding


High-dynamic-range (HDR) video streams have been delivered through high-efficiency video coding (HEVC). HDR video tone mapping is required additionally but is operated separately to adjust the content’s dynamic range for each display device. HDR video tone mapping and HEVC encoding share common computational processes for spatial and temporal coherence in a video stream; however, they have been developed and implemented independently with their own computational budgets.

Paper Details

Authors:
Mingyun Kang, Joo Ho Lee, Inchang Choi, Min H. Kim
Submitted On:
18 September 2019 - 6:34am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019_poster_v10.pdf

(0)

Subscribe

[1] Mingyun Kang, Joo Ho Lee, Inchang Choi, Min H. Kim, "Real-Time HDR Video Tone Mapping Using High Efficiency Video Coding", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4670. Accessed: Sep. 20, 2019.
@article{4670-19,
url = {http://sigport.org/4670},
author = {Mingyun Kang; Joo Ho Lee; Inchang Choi; Min H. Kim },
publisher = {IEEE SigPort},
title = {Real-Time HDR Video Tone Mapping Using High Efficiency Video Coding},
year = {2019} }
TY - EJOUR
T1 - Real-Time HDR Video Tone Mapping Using High Efficiency Video Coding
AU - Mingyun Kang; Joo Ho Lee; Inchang Choi; Min H. Kim
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4670
ER -
Mingyun Kang, Joo Ho Lee, Inchang Choi, Min H. Kim. (2019). Real-Time HDR Video Tone Mapping Using High Efficiency Video Coding. IEEE SigPort. http://sigport.org/4670
Mingyun Kang, Joo Ho Lee, Inchang Choi, Min H. Kim, 2019. Real-Time HDR Video Tone Mapping Using High Efficiency Video Coding. Available at: http://sigport.org/4670.
Mingyun Kang, Joo Ho Lee, Inchang Choi, Min H. Kim. (2019). "Real-Time HDR Video Tone Mapping Using High Efficiency Video Coding." Web.
1. Mingyun Kang, Joo Ho Lee, Inchang Choi, Min H. Kim. Real-Time HDR Video Tone Mapping Using High Efficiency Video Coding [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4670

Discrete Cosine Basis Oriented Motion Modeling for Fisheye and 360 Degree Video Coding


Motion modeling plays a central role in video compression. This role is even more critical in fisheye video sequences
since the wide-angle fisheye imagery has special characteristics as in exhibiting radial distortion. While the translational motion model employed by modern video coding standards, such as HEVC, is sufficient in most cases, using higher order models is
beneficial; for this reason, the upcoming video coding standard, VVC, employs a 4-parameter affine model. Discrete cosine basis

Paper Details

Authors:
Ashek Ahmmed, Manoranjan Paul
Submitted On:
18 September 2019 - 5:18am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Motion modelling for 360 videos

(2)

Subscribe

[1] Ashek Ahmmed, Manoranjan Paul, "Discrete Cosine Basis Oriented Motion Modeling for Fisheye and 360 Degree Video Coding", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4668. Accessed: Sep. 20, 2019.
@article{4668-19,
url = {http://sigport.org/4668},
author = {Ashek Ahmmed; Manoranjan Paul },
publisher = {IEEE SigPort},
title = {Discrete Cosine Basis Oriented Motion Modeling for Fisheye and 360 Degree Video Coding},
year = {2019} }
TY - EJOUR
T1 - Discrete Cosine Basis Oriented Motion Modeling for Fisheye and 360 Degree Video Coding
AU - Ashek Ahmmed; Manoranjan Paul
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4668
ER -
Ashek Ahmmed, Manoranjan Paul. (2019). Discrete Cosine Basis Oriented Motion Modeling for Fisheye and 360 Degree Video Coding. IEEE SigPort. http://sigport.org/4668
Ashek Ahmmed, Manoranjan Paul, 2019. Discrete Cosine Basis Oriented Motion Modeling for Fisheye and 360 Degree Video Coding. Available at: http://sigport.org/4668.
Ashek Ahmmed, Manoranjan Paul. (2019). "Discrete Cosine Basis Oriented Motion Modeling for Fisheye and 360 Degree Video Coding." Web.
1. Ashek Ahmmed, Manoranjan Paul. Discrete Cosine Basis Oriented Motion Modeling for Fisheye and 360 Degree Video Coding [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4668

EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE


Screen content videos (SCVs) are becoming popular in many applications. Compared with natural content videos (NCVs), the SCVs have different characteristics. Therefore, the screen content coding (SCC) based on HEVC adopts some new coding tools (intra block copy and palette mode etc.) to improve coding efficiency, but these tools increase the computational complexity as well. In this paper, we propose to predict the CU partition of the SCVs by a convolutional neural network

Paper Details

Authors:
zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen
Submitted On:
20 September 2019 - 4:18am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019_poster_L.Zhao

(0)

Subscribe

[1] zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen, "EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4614. Accessed: Sep. 20, 2019.
@article{4614-19,
url = {http://sigport.org/4614},
author = {zhiwen wei; weitong cai; wenyi wang; liaoyuan zeng and jianwen chen },
publisher = {IEEE SigPort},
title = {EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE},
year = {2019} }
TY - EJOUR
T1 - EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE
AU - zhiwen wei; weitong cai; wenyi wang; liaoyuan zeng and jianwen chen
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4614
ER -
zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen. (2019). EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE. IEEE SigPort. http://sigport.org/4614
zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen, 2019. EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE. Available at: http://sigport.org/4614.
zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen. (2019). "EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE." Web.
1. zhiwen wei, weitong cai, wenyi wang, liaoyuan zeng and jianwen chen. EFFICIENT SCREEN CONTENT CODING BASED ON CONVOLUTIONAL NEURAL NETWORK GUIDED BY A LARGE-SCALE DATABASE [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4614

Fast Inpainting-based Compression: Combinging Shepard Interpolation with Joint Inpainting and Prediction


Inpainting-based compression has been suggested as a qualitative competitor to the JPEG family of transform-based codecs, specifically for high compression ratios. However, it also requires sophisticated interpolation, data optimisation and encoding tasks that are both slow and hard to implement. We propose a fast and simple alternative that combines Shepard interpolation with a novel joint inpainting and prediction approach. It represents the image by a fraction of its pixel values on a sparse regular subgrid that are selected by an efficient optimisation strategy.

Paper Details

Authors:
Pascal Peter
Submitted On:
12 September 2019 - 9:03am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster-icip19-static.pdf

(6)

Subscribe

[1] Pascal Peter, "Fast Inpainting-based Compression: Combinging Shepard Interpolation with Joint Inpainting and Prediction", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4604. Accessed: Sep. 20, 2019.
@article{4604-19,
url = {http://sigport.org/4604},
author = {Pascal Peter },
publisher = {IEEE SigPort},
title = {Fast Inpainting-based Compression: Combinging Shepard Interpolation with Joint Inpainting and Prediction},
year = {2019} }
TY - EJOUR
T1 - Fast Inpainting-based Compression: Combinging Shepard Interpolation with Joint Inpainting and Prediction
AU - Pascal Peter
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4604
ER -
Pascal Peter. (2019). Fast Inpainting-based Compression: Combinging Shepard Interpolation with Joint Inpainting and Prediction. IEEE SigPort. http://sigport.org/4604
Pascal Peter, 2019. Fast Inpainting-based Compression: Combinging Shepard Interpolation with Joint Inpainting and Prediction. Available at: http://sigport.org/4604.
Pascal Peter. (2019). "Fast Inpainting-based Compression: Combinging Shepard Interpolation with Joint Inpainting and Prediction." Web.
1. Pascal Peter. Fast Inpainting-based Compression: Combinging Shepard Interpolation with Joint Inpainting and Prediction [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4604

Pages