Minimum Description Length Sparse Modeling and Region Merging for Lossless Plenoptic Image Compression

Helin, Petri; Astola, Pekka; Rao, Bhaskar D.; Tăbuş, Ioan

doi:10.1109/jstsp.2017.2737967

Cited by 20 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(M1) the JPEG 2000 codec [29] based on the OpenJPEG implementation [33], the active reference software for JPEG 2000 [34], where the code runs with the "−r 1" parameter for a lossless compression setting; (M2) the HEVC video codec [13] with all intra configuration; HEVC encodes the pseudo-video-sequence created using the spiral stacking scan pattern [10,12] [6], our preliminary work on MP-wise prediction, where the models are trained based on patches selected from the same training set; (M8) the PredNN method [4], the first paper on pixel-wise CNN-based prediction, where the model is trained based on patches collected from the same training set; for each LF image more than 183 million patches are processed, one for each pixel and for each color matrix; (M9) the REP-CNN method [5], the first deep-learningbased dual prediction method for pixel-wise prediction based on a similar training process as M8; (M10) the proposed MPSC-CNN codec employed for the 2 × 2 configuration of reference views; (M11) the proposed MPSC-CNN codec employed for the 3 × 3 configuration of reference views;…”

Section: B) Lossless Compression Resultsmentioning

confidence: 99%

“…In [9], a method based on a predictive coding approach is proposed for raw plenoptic image compression. In [10], the method encodes the LF image as a set of views using a sparse modeling predictor guided by a disparity-based image segmentation. In [11], the authors proposed a context modeling method for compressing each view based on one reference view.…”

Section: State-of-the-artmentioning

confidence: 99%

“…The performance of the following methods is compared: the JPEG 2000 codec [29] based on the OpenJPEG implementation [33], the active reference software for JPEG 2000 [34], where the code runs with the “ −r 1 ” parameter for a lossless compression setting;the HEVC video codec [13] with all intra configuration; HEVC encodes the pseudo-video-sequence created using the spiral stacking scan pattern [10,12]; the fast x265 library [35] is used with the veryslow preset and the lossless parameter;the JPEG-LS codec [1];the CALIC codec [2] based on the authors implementation available online [36];the CMS method [11] designed to encode 193 views out of the 225 views, where the remaining views are encoded using CALIC [2];the FLIF codec [3] based on the implementation available online [7];the MP-CNN method [6], our preliminary work on MP-wise prediction, where the models are trained based on patches selected from the same training set;the PredNN method [4], the first paper on pixel-wise CNN-based prediction, where the model is trained based on patches collected from the same training set; for each LF image more than 183 million patches are processed, one for each pixel and for each color matrix;the REP-CNN method [5], the first deep-learning-based dual prediction method for pixel-wise prediction based on a similar training process as M8;the proposed MPSC-CNN codec employed for the configuration of reference views;the proposed MPSC-CNN codec employed for the configuration of reference views;the proposed MPSC-CNN codec employed for the configuration of reference views;the proposed MPSC-CNN codec employed for the configuration of reference views.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…the HEVC video codec [13] with all intra configuration; HEVC encodes the pseudo-video-sequence created using the spiral stacking scan pattern [10,12]; the fast x265 library [35] is used with the veryslow preset and the lossless parameter;…”

Section: Experimental Evaluationmentioning

confidence: 99%

See 3 more Smart Citations

Deep-learning-based macro-pixel synthesis and lossless coding of light field images

Schiopu

Munteanu

2019

SIP

View full text Add to dashboard Cite

Deep-learning-based macro-pixel synthesis and lossless coding of light field imagesionut schiopu and adrian munteanu This paper proposes a novel approach for lossless coding of light field (LF) images based on a macro-pixel (MP) synthesis technique which synthesizes the entire LF image in one step. The reference views used in the synthesis process are selected based on four different view configurations and define the reference LF image. This image is stored as an array of reference MPs which collect one pixel from each reference view, being losslessly encoded as a base layer. A first contribution focuses on a novel network design for view synthesis which synthesizes the entire LF image as an array of synthesized MPs. A second contribution proposes a network model for coding which computes the MP prediction used for lossless encoding of the remaining views as an enhancement layer. Synthesis results show an average distortion of 29.82 dB based on four reference views and up to 36.19 dB based on 25 reference views. Compression results show an average improvement of 29.9 over the traditional lossless image codecs and 9.1 over the state-of-the-art.

show abstract

Section: B) Lossless Compression Resultsmentioning

confidence: 99%

Section: State-of-the-artmentioning

confidence: 99%

Section: Experimental Evaluationmentioning

confidence: 99%

Section: Experimental Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Deep-learning-based macro-pixel synthesis and lossless coding of light field images

Schiopu

Munteanu

2019

SIP

View full text Add to dashboard Cite

show abstract

“…For applications on more complex data, the MDL-based segmentation of depth maps was studied in [ 29 ] for the lossless compression of light fields.…”

Section: Introductionmentioning

confidence: 99%

Information Theoretic Modeling of High Precision Disparity Data for Lossy Compression and Object Segmentation

Tăbuş¹,

Kaya

2019

Entropy

View full text Add to dashboard Cite

In this paper, we study the geometry data associated with disparity map or depth map images in order to extract easy to compress polynomial surface models at different bitrates, proposing an efficient mining strategy for geometry information. The segmentation, or partition of the image pixels, is viewed as a model structure selection problem, where the decisions are based on the implementable codelength of the model, akin to minimum description length for lossy representations. The intended usage of the extracted disparity map is to provide to the decoder the geometry information at a very small fraction from what is required for a lossless compressed version, and secondly, to convey to the decoder a segmentation describing the contours of the objects from the scene. We propose first an algorithm for constructing a hierarchical segmentation based on the persistency of the contours of regions in an iterative re-estimation algorithm. Then, we propose a second algorithm for constructing a new sequence of segmentations, by selecting the order in which the persistent contours are included in the model, driven by decisions based on the descriptive codelength. We consider real disparity datasets which have the geometry information at a high precision, in floating point format, but for which encoding of the raw information, in about 32 bits per pixels, is too expensive, and we then demonstrate good approximations preserving the object structure of the scene, achieved for rates below 0.2 bits per pixels.

show abstract

An effective image compression technique based on burrows wheeler transform with set partitioning in hierarchical trees

Dhenakaran

2021

Concurrency and Computation

View full text Add to dashboard Cite

In this article, the efficient image compression which consists of Burrows–Wheeler transform (BWT) with set partitioning in hierarchical trees (SPIHT). The main phases of the proposed system are: partitioning, compression of non‐ROI areas, Fusion and compression of ROI areas. To enhance the propose of the proposed methodology, the morphological functions are updated by dividing two types of images with the consideration of dilation and erosion control. After that, the convolution and correlation in the deformation provide good accuracy of the segmentation at the fastest speed. In this proposed methodology, SPIHT encryption is a lossy compression technique aimed at understanding the non‐ROI area, while the BWT is a lossless compression technique performed to achieve a summary of the ROI area. Finally, separating these two parts of the image merges the image and reconstructs it to the desired quality. The test sends a variety of images and analyzes the performance of the proposed system using compression ratio and PSNR measurements.

show abstract

Minimum Description Length Sparse Modeling and Region Merging for Lossless Plenoptic Image Compression

Cited by 20 publications

References 23 publications

Deep-learning-based macro-pixel synthesis and lossless coding of light field images

Deep-learning-based macro-pixel synthesis and lossless coding of light field images

Information Theoretic Modeling of High Precision Disparity Data for Lossy Compression and Object Segmentation

An effective image compression technique based on burrows wheeler transform with set partitioning in hierarchical trees

Contact Info

Product

Resources

About