Robust Learning of 2-D Separable Transforms for Next-Generation Video Coding

@article{Sezer2011RobustLO,
  title={Robust Learning of 2-D Separable Transforms for Next-Generation Video Coding},
  author={Osman Gokhan Sezer and Robert A. Cohen and Anthony Vetro},
  journal={2011 Data Compression Conference},
  year={2011},
  pages={63-72}
}
With the simplicity of its application together with compression efficiency, the Discrete Cosine Transform(DCT) plays a vital role in the development of video compression standards. For next-generation video coding, a new set of 2-D separable transforms has emerged as a candidate to replace the DCT. These separable transforms are learned from residuals of each intra prediction mode, hence termed as Mode dependent-directional transforms (MDDT). MDDT uses the Karhunen-Loeve Transform (KLT) to… 

Figures and Tables from this paper

Data-driven Optimization of Row-Column Transforms for Block-Based Hybrid Video Compression

TLDR
A method for training structured transforms by maximizing the data likelihood under a parameterized probabilistic model with a compelled structure is described and it is shown that trained row-column transforms achieve almost the same coding gain as unconstrained KLTs when applied as secondary transforms.

Annealed learning based block transforms for HEVC video coding

  • S. PuriS. LasserreP. Callet
  • Computer Science
    2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2016
TLDR
A new on-the-fly block-based transform optimization technique which involves first the classification of the residual blocks based on the cost of encoding the block, and then the generation of new optimized transforms for each class is proposed.

Multiview video compression with 1-D transforms

Internal-video mode dependent directional transform

TLDR
An internal-video mode dependent directional transform in HEVC for intra coding that can capture the statistical characteristics of the coded video clip and provide efficient transforms.

Improved coefficient coding for adaptive transforms in HEVC

TLDR
This paper proposes to further improve the previously proposed learning scheme by improving the coding of transformed coefficients in context to the online learning of transforms by improves the convergence of the learning scheme and improves the compression efficiency.

Efficient H.264/AVC Video Coding with Adaptive Transforms

TLDR
A novel content adaptive transform framework for the H.264/AVC-based video coding by utilizing pixel rearrangement to dynamically adjust the transform kernels to adapt to the video content and a spiral-scanning method is developed to reorder the transform coefficients for better entropy coding.

Rate-Distortion Optimized Transforms Based on the Lloyd-Type Algorithm for Intra Block Coding

TLDR
This paper proposes a novel rate-distortion optimized transform (RDOT) scheme which allows a set of specially trained transforms to be available to all modes, and each block can choose its preferred transform to minimize the rate- Distortion (RD) cost.

Variable Block-Sized Signal-Dependent Transform for Video Coding

TLDR
This paper presents a variable block-sized signal-dependent transforms (SDTs) design based on the High Efficiency Video Coding (HEVC) framework and presents a fast algorithm for transform derivation, which shows the effectiveness of the SDTs for different block sizes.

Approximation and Compression With Sparse Orthonormal Transforms

TLDR
This work designs sparse orthonormal transforms (SOTs) that automatically exploit regularity over different signal structures and provides an adaptation method that determines the best representation over localized regions and provides consistent increase in compression and approximation performance compared with conventional methods.

Design and Optimization of Graph Transform for Image and Video Compression

TLDR
This thesis presents a new directional transform, called Steerable Discrete Cosine Transform (SDCT), which can be obtained by steering the 2D-DCT basis in any chosen direction and it outperforms the classical DCT and other directional transforms.

References

SHOWING 1-10 OF 15 REFERENCES

Sparse orthonormal transforms for image compression

TLDR
A block-based transform optimization and associated image compression technique that exploits regularity along directional image singularities and an EZW/SPIHT like entropy coder is used to encode the transform coefficients to show that the designs have competitive rate-distortion performance.

Joint sparsity-based optimization of a set of orthonormal 2-D separable block transforms

TLDR
An iterative method for the optimization of a set of 2-D separable transforms for a given training data set, each one being optimal for a subset of the data with respect to a sparsity-based objective function.

Improved h.264 intra coding based on bi-directional intra prediction, directional transform, and adaptive coefficient scanning

  • Yan YeM. Karczewicz
  • Computer Science
    2008 15th IEEE International Conference on Image Processing
  • 2008
TLDR
Together the improvements can bring on average 7% and 10% coding gain for CABAC and for CAVLC, respectively, with average coding gain of 12% for HD sequences.

A Framework for Robust Subspace Learning

TLDR
The theory of Robust Subspace Learning (RSL) for linear models within a continuous optimization framework based on robust M-estimation is developed and applies to a variety of linear learning problems in computer vision including eigen-analysis and structure from motion.

A comparative study of JPEG2000, AVC/H.264, and HD photo

TLDR
The overall performance of rate-distortion performance between JPEG 2000, AVC/H.264 High 4:4:4 Intra and HD Photo is quite comparable for the three coding approaches, within an average range of ±10% in bitrate variations, and outperforming the conventional JPEG.

The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields

TLDR
A framework based on robust estimation is presented that addresses violations of the brightness constancy and spatial smoothness assumptions caused by multiple motions of optical flow, and is applied to standard formulations of the optical flow problem thus reducing their sensitivity to violations of their underlying assumptions.

Principal Component Analysis with Missing Data and Its Application to Polyhedral Object Modeling

TLDR
A weighted least-squares (WLS) approach which simultaneously recovers object shape and transformation among different views without recovering interframe motion is developed and is robust against noise and mismatching and generates accurate polyhedral object models.

On comparing JPEG2000 and intraframe AVC

TLDR
The results show that JPEG2000 is very competitive with AVC High Profile Intra and outperforms the Main Profile and performs better than both Profiles of AVC Intra for Intermediate and low spatial resolution sequences.

EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation

TLDR
A “subspace constancy assumption” is defined that allows techniques for parameterized optical flow estimation to simultaneously solve for the view of an object and the affine transformation between the eigenspace and the image.

Robust principal component analysis by self-organizing rules based on statistical physics approach

TLDR
The authors' robust rules improve the performances of the existing PCA algorithms significantly when outliers are present and perform excellently for fulfilling various PCA-like tasks such as obtaining the first principal component vector, the first k principal component vectors, and directly finding the subspace spanned by the firstk vector principal components vectors without solving for each vector individually.