A proof-of-concept framework for PDE-based video compression

Andris, Sarah; Peter, Pascal; Weickert, Joachim

doi:10.1109/pcs.2016.7906362

Cited by 25 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this approach compresses each frame individually and does not exploit temporal redundancies. Andris et al [13] proposed a proof-of-concept video codec that additionally uses optical flow methods for inter frame prediction. The motion fields are compressed with a simple subsampling, resulting again in block artefacts.…”

Section: B Related Workmentioning

confidence: 99%

Compressing Flow Fields with Edge-Aware Homogeneous Diffusion Inpainting

Jost

Peter

Weickert

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Motion estimation is an important component of video codecs and various applications in computer vision. Especially in video compression the compact representation of motion fields is crucial, as modern video codecs use them for inter frame prediction. In recent years compression methods relying on diffusion-based inpainting have been becoming an increasingly competitive alternative to classical transform-based codecs. They perform particularly well on piecewise smooth data, suggesting that motion fields can be efficiently represented by such approaches. However, they have so far not been used for the compression of motion data. Therefore, we assess the potential of flow field compression based on homogeneous diffusion with a specifically designed new framework: Our codec stores only a few representative flow vectors and reconstructs the flow field with edge-aware homogeneous diffusion inpainting. Additionally stored edge data thereby ensure the accurate representation of discontinuities in the flow field. Our experiments show that this approach can outperform state-of-the-art codecs such as JPEG2000 and BPG/HEVC intra.

show abstract

Section: B Related Workmentioning

confidence: 99%

Compressing Flow Fields with Edge-Aware Homogeneous Diffusion Inpainting

Jost

Peter

Weickert

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…While the procedure above resembles the one from the former subsection, the treatment of overlapping blocks has different interpretations to the optimizations in (25) and (26). Indeed, note that the block-level rate-distortion optimizations in (26) are not discrete due to the extended bit-cost evaluation r v (·) defined in (21). Due to the definition ofr v (·), the ratedistortion optimizations (26) can be considered as continuous relaxations of the discrete optimizations done by the practical compression technique.…”

Section: B Regularize Total Complexity Of All Overlapping Blocksmentioning

confidence: 99%

“…Indeed, note that the block-level rate-distortion optimizations in (26) are not discrete due to the extended bit-cost evaluation r v (·) defined in (21). Due to the definition ofr v (·), the ratedistortion optimizations (26) can be considered as continuous relaxations of the discrete optimizations done by the practical compression technique. Since we intend using a given compression method without explicit knowledge of its underlying codebook, we cannot construct the voronoi cells defininḡ r v (·) and, thus, it is impractical to accurately solve (26).…”

Section: B Regularize Total Complexity Of All Overlapping Blocksmentioning

confidence: 99%

“…Due to the definition ofr v (·), the ratedistortion optimizations (26) can be considered as continuous relaxations of the discrete optimizations done by the practical compression technique. Since we intend using a given compression method without explicit knowledge of its underlying codebook, we cannot construct the voronoi cells defininḡ r v (·) and, thus, it is impractical to accurately solve (26). Consequently, we suggest to approximate the optimizations (26) by the discrete forms of…”

Section: B Regularize Total Complexity Of All Overlapping Blocksmentioning

confidence: 99%

“…Moreover, we also extend our evaluation given in [9] for image inpainting, where here we use the JPEG2000 and HEVC compression standards in our ADMM-based approach to restore images from a severe degradation of 80% missing pixels. Interestingly, our compression-based image inpainting approach can be perceived as the dual concept of inpainting-based compression of images and videos suggested in, e.g., [24]- [26] and discussed also in [27].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Restoration by Compression

Dar

Elad

Bruckstein

2018

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

In this paper we study the topic of signal restoration using complexity regularization, quantifying the compression bit-cost of the signal estimate. While complexity-regularized restoration is an established concept, solid practical methods were suggested only for the Gaussian denoising task, leaving more complicated restoration problems without a generally constructive approach. Here we present practical methods for complexity-regularized restoration of signals, accommodating deteriorations caused by a known linear degradation operator of an arbitrary form. Our iterative procedure, obtained using the alternating direction method of multipliers (ADMM) approach, addresses the restoration task as a sequence of simpler problems involving 2-regularized estimations and rate-distortion optimizations (considering the squared-error criterion). Further, we replace the rate-distortion optimizations with an arbitrary standardized compression technique and thereby restore the signal by leveraging underlying models designed for compression. Additionally, we propose a shift-invariant complexity regularizer, measuring the bit-cost of all the shifted forms of the estimate, extending our method to use averaging of decompressed outputs gathered from compression of shifted signals. On the theoretical side, we present an analysis of complexity-regularized restoration of a cyclo-stationary Gaussian signal from deterioration by a linear shift-invariant operator and an additive white Gaussian noise. The theory shows that optimal complexity-regularized restoration relies on an elementary restoration filter and compression spreading reconstruction quality unevenly based on the energy distribution of the degradation filter. Nicely, these ideas are realized also in the proposed practical methods. Finally, we present experiments showing good results for image deblurring and inpainting using the JPEG2000 and HEVC compression standards.

show abstract