Fast Inpainting-Based Compression: Combining Shepard Interpolation with Joint Inpainting and Prediction

Peter, Pascal

doi:10.1109/icip.2019.8803760

Cited by 12 publications

(22 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some ANS encoders and decoders have been shown to allow for very fast software implementations in modern CPUs [4], [5]. This has lead to its incorporation in recent data compression standards and its use in many different cases [6], [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18], [19]. In addition, ANS-based encoders could be applicable to a very wide range of multimedia scenarios, such as an alternative to the Rice-Golomb codes employed in the energy-efficient scheme described in [20], as a high-throughput entropy encoder in a high frame rate video format [21], or in general as an entropy encoder in schemes for sparse coding [22], learned image compression [23], compressive sensing [24], or point cloud data compression [25].…”

Section: Introductionmentioning

confidence: 99%

Redundancy and Optimization of tANS Entropy Encoders

Blanes¹,

Hernández-Cabronero²,

Serra-Sagristà³

et al. 2021

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Nowadays entropy encoders are part of almost all data compression methods, with the Asymmetrical Numeral Systems (ANS) family of entropy encoders having recently risen in popularity. Entropy encoders based on the tabled variant of ANS are known to provide varying performances depending on their internal design. In this paper, we present a method that calculates encoder redundancies in almost linear time, which translates in practice to thousand-fold speedups in redundancy calculations for small automatons, and allows redundancy calculations for automatons with tens of millions of states that would be otherwise prohibitive. We also address the problem of improving tabled ANS encoder designs, by employing the aforementioned redundancy calculation method in conjunction with a stochastic hill climbing strategy. The proposed approach consistently outperforms state-of-the-art methods in tabled ANS encoder design. For automatons of twice the alphabet size, experimental results show redundancy reductions around 10% over the default initialization method and over 30% for random initialization.

show abstract

Section: Introductionmentioning

confidence: 99%

Redundancy and Optimization of tANS Entropy Encoders

Blanes¹,

Hernández-Cabronero²,

Serra-Sagristà³

et al. 2021

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…Implicitly, many inpainting-based compression approaches (e.g. [6,13,16]) and associated mask optimisation strategies (e.g. [1,4,10]) rely on these sparsification scale-spaces: They choose sparse masks as a compact representation of the image and aim for an accurate reconstruction from this known data.…”

Section: Introductionmentioning

confidence: 99%

“…However, there is another aspect of compression, that has hitherto not been explored from a scale-space perspective: The known data has to be stored, which means the information content of the grey or colour values plays an important role. In particular, all contemporary compression codecs use some form of quantisation combined with variants of entropy coding, no matter if they rely on transforms [12,19], inpainting [6,13,16], or neural networks [14]. Quantisation reduces the amount of different admissible values in the co-domain to lower the Shannon entropy [18], the measure for information content.…”

Section: Introductionmentioning

confidence: 99%

Quantisation Scale-Spaces

Peter¹

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, sparsification scale-spaces have been obtained as a sequence of inpainted images by gradually removing known image data. Thus, these scale-spaces rely on spatial sparsity. In the present paper, we show that sparsification of the co-domain, the set of admissible grey values, also constitutes scale-spaces with induced hierarchical quantisation techniques. These quantisation scale-spaces are closely tied to information theoretical measures for coding cost, and therefore particularly interesting for inpainting-based compression. Based on this observation, we propose a sparsification algorithm for the grey-value domain that outperforms uniform quantisation as well as classical clustering approaches.

show abstract

“…Existing works on image compression with adaptive sampling such as [20] use content adaptive sampling patterns that are not dynamic, i.e., the information on the sampling positions needs to be coded, too. In contrast to that, the sampling pattern in [21] is fixed and does not need to be coded. For future compression frameworks based on dynamic sampling, the advantages from both approaches could be combined.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Image Sampling Using a Novel Variance Based Probability Mass Function

Grosche

Koller

Seiler

et al. 2020

IEEE Trans. Comput. Imaging

View full text Add to dashboard Cite

Incremental sampling can be applied in scientific imaging techniques whenever the measurements are taken incrementally, i.e., one pixel position is measured at a time. It can be used to reduce the measurement time as well as the dose impinging onto a specimen. For incremental sampling, the choice of the sampling pattern plays a major role in order to achieve a high reconstruction quality. Besides using static incremental sampling patterns, it is also possible to dynamically adapt the sampling pattern based on the already measured data. This is called dynamic sampling and allows for a higher reconstruction quality, as the inhomogeneity of the sampled image content can be taken into account. Several approaches for dynamic sampling have been published in the literature. However, they share the common drawback that homogeneous regions are sampled too late. This reduces the reconstruction quality as fine details can be missed. We overcome this drawback using a novel probabilistic approach to dynamic image sampling (PADIS). It is based on a data driven probability mass function which uses a local variance map. In our experiments, we evaluate the reconstruction quality for scanning electron microscopy images as well as for natural image content. For scanning electron microscopy images with a sampling density of 35% and frequency selective reconstruction, our approach achieves a PSNR gain of +0.92 dB compared to other dynamic sampling approaches and +1.42 dB compared to the best static patterns. For natural images, even higher gains are achieved. Experiments with additional measurement noise show that for our method the sampling patterns are more stable. Moreover, the runtime is faster than for the other methods.

show abstract

Fast Inpainting-Based Compression: Combining Shepard Interpolation with Joint Inpainting and Prediction

Cited by 12 publications

References 16 publications

Redundancy and Optimization of tANS Entropy Encoders

Redundancy and Optimization of tANS Entropy Encoders

Quantisation Scale-Spaces

Dynamic Image Sampling Using a Novel Variance Based Probability Mass Function

Contact Info

Product

Resources

About