Intra-Frame Coding Using a Conditional Autoencoder

Brand, Fabian; Seiler, Jurgen; Kaup, André

doi:10.1109/jstsp.2020.3034768

Cited by 20 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These authors argued that the coding performance of the proposed intra prediction was typically obtained from the coding blocks with complex textures when integrated into the HEVC's intra prediction module. Brand et al [20] introduced the concept of conditional autoencoder (CAE)-based intra prediction for all color components. The CAE-based method can generate several prediction modes using one network.…”

Section: Related Workmentioning

confidence: 99%

Coarse-to-Fine Network-Based Intra Prediction in Versatile Video Coding

Park,

Moon,

et al. 2023

Sensors

View full text Add to dashboard Cite

After the development of the Versatile Video Coding (VVC) standard, research on neural network-based video coding technologies continues as a potential approach for future video coding standards. Particularly, neural network-based intra prediction is receiving attention as a solution to mitigate the limitations of traditional intra prediction performance in intricate images with limited spatial redundancy. This study presents an intra prediction method based on coarse-to-fine networks that employ both convolutional neural networks and fully connected layers to enhance VVC intra prediction performance. The coarse networks are designed to adjust the influence on prediction performance depending on the positions and conditions of reference samples. Moreover, the fine networks generate refined prediction samples by considering continuity with adjacent reference samples and facilitate prediction through upscaling at a block size unsupported by the coarse networks. The proposed networks are integrated into the VVC test model (VTM) as an additional intra prediction mode to evaluate the coding performance. The experimental results show that our coarse-to-fine network architecture provides an average gain of 1.31% Bjøntegaard delta-rate (BD-rate) saving for the luma component compared with VTM 11.0 and an average of 0.47% BD-rate saving compared with the previous related work.

show abstract

Section: Related Workmentioning

confidence: 99%

Coarse-to-Fine Network-Based Intra Prediction in Versatile Video Coding

Park,

Moon,

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Recently, learning-based methods for the use in video coding have been proposed. These methods often tackle prediction problems, such as [15] which proposes a deeplearning-based intra-prediction method for use in VVC. Also, VVC includes Matrix Intra Prediction (MIP) [16], which includes a trained matrix.…”

Section: Related Workmentioning

confidence: 99%

A Low-Parametric Model for Bit-Rate Estimation of VVC Residual Coding

Brand¹,

Herglotz²,

Schober³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

There are many tasks within video compression which require fast bit rate estimation. As an example, rate-control algorithms are only feasible because it is possible to estimate the required bit rate without needing to encode the entire block. With residual coding technology becoming more and more sophisticated, the corresponding bit rate models require more advanced features. In this work, we propose a set of four features together with a linear model, which is able to estimate the rate of arbitrary residual blocks which were compressed using the VVC standard. Our method outperforms other methods which were used for the same task both in terms of mean absolute error and mean relative error. Our model deviates by less than 4 bit on average over a large dataset of natural images.

show abstract

“…Hybrid video coders typically use multi mode prediction, a combination of angular, DC and planar prediction. Recently many methods were proposed to employ neural network for block based intra prediction, for example in [6,7,8].…”

Section: Prior Artmentioning

confidence: 99%

“…Using the properties discussed in the previous subsection, we now propose an algorithm which modifies a whole motion field at the encoder in a way that it afterwards incorporates intra prediction according to (7).…”

Section: I2i Motion Field Processingmentioning

confidence: 99%

Intra To Inter: Towards Intra Prediction for Learning-Based Video Coders Using Optical Flow

Brand

Seiler

Kaup

2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Traditional video coders often rely on a block structure for transmission. Here each block is coded separately and sequentially and for each block the encoder can decide whether to use intra or inter prediction. This way, inter and intra prediction can be mixed within a single frame. This has advantages when new areas are uncovered, which were not present in the reference frame, and can hence not be predicted well. These areas are typically predicted using intra prediction. Currently much research goes into end-to-end-trained video coders which do not operate on a block level and typically use dense motion fields for inter prediction. There it is more difficult to incorporate intra prediction for uncovered regions. In this paper we propose a novel concept which enables us to reinterpret classical angular intra prediction in a way that we can transmit it as part of the dense motion field. We can save an average of 18% rate for the transmission of the motion vectors for the same quality of the prediction image.

show abstract

Intra-Frame Coding Using a Conditional Autoencoder

Cited by 20 publications

References 23 publications

Coarse-to-Fine Network-Based Intra Prediction in Versatile Video Coding

Coarse-to-Fine Network-Based Intra Prediction in Versatile Video Coding

A Low-Parametric Model for Bit-Rate Estimation of VVC Residual Coding

Intra To Inter: Towards Intra Prediction for Learning-Based Video Coders Using Optical Flow

Contact Info

Product

Resources

About