Intra Prediction and Mode Coding in VVC

Pfaff, Jonathan; Filippov, Alexey; Liu, Shan; Zhao, Xin; Chen, Jianle; De-Luxan-Hernandez, Santiago; Wiegand, Thomas; Rufitskiy, Vasily; Ramasubramonian, Adarsh K.; Auwera, Geert Van Der

doi:10.1109/tcsvt.2021.3072430

Cited by 82 publications

(29 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BD-rate is averaged using all test images in Kodak dataset. RGB images are directly encoded under 444 mode [11], [12]. The proposed method reports the best performance with less MACs/pixel and parameters.…”

Section: Background and Motivationmentioning

confidence: 99%

High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation

Lu¹,

Ma²

2022

Preprint

View full text Add to dashboard Cite

Questing for lossy image coding (LIC) with superior efficiency on both compression performance and computation throughput is challenging. The vital factor behind is how to intelligently explore Adaptive Neighborhood Information Aggregation (ANIA) in transform and entropy coding modules. To this aim, Integrated Convolution and Self-Attention (ICSA) unit is first proposed to form content-adaptive transform to dynamically characterize and embed neighborhood information conditioned on the input. Then a Multistage Context Model (MCM) is developed to stagewisely execute context prediction using necessary neighborhood elements for accurate and parallel entropy probability estimation. Both ICSA and MCM are stacked under a Variational Auto-Encoder (VAE) architecture to derive rate-distortion optimized compact representation of input image via end-to-end training. Our method reports the superior compression performance surpassing the VVC Intra with ≈15% BD-rate improvement averaged across Kodak, CLIC and Tecnick datasets; and also demonstrates ≈10× speedup of image decoding when compared with other notable learned LIC approaches. All materials are made publicly accessible at https://njuvision.github.io/TinyLIC for reproducible research.

show abstract

Section: Background and Motivationmentioning

confidence: 99%

High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation

Lu¹,

Ma²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Intra coding principal takes advantage of spatial correlation existing in local image texture. To decorrelate them, a series of coding tools are provided in VVC which are tied with partitioning and a set of Intra prediction modes (IPMs) [13]. For the block partitioning, in addition to the principals explained in previous section, a new tool called dual-tree is introduced which allows separate partitioning trees for luma and chroma channel types.…”

Section: B Intra Coding Toolsmentioning

confidence: 99%

Versatile Video Coding Standard: A Review from Coding Tools to Consumers Deployment

Hamidouche¹,

Biatek²,

Abdoli³

et al. 2021

Preprint

View full text Add to dashboard Cite

The amount of video content and the number of applications based on multimedia information increase each day. The development of new video coding standards is a challenge to increase the compression rate and other important features with a reasonable increase in the computational load. Video Experts Team (JVET) of ITU-T and the JCT group within ISO/IEC have worked together to standardize the Versatile Video Coding, approved finally in July 2020 as ITU-T H.266 -MPEG-I -Part 3 (ISO/IEC 23090-3) standard. This paper overviews some interesting consumer electronic use cases, the compression tools described in the standard, the current available real time implementations and the first industrial trials done with this standard.

show abstract

“…Voxel Sampling Layer. We embed voxel upscaling in SOPA and voxel downscaling in SLNE 4 to execute the crossscale message passing (see red painted voxel sampling layer in Fig. 3b and Fig.…”

Section: Basic Sparsecnn Architecturementioning

confidence: 99%

“…In compression of 2D images or video frames, because their spatially-connected pixels are mostly well-arranged following local structural patterns on a 2D plane, we can model the "context" by conveniently accessing neighborhood pixels [4] to exploit inter-correlation. However, for an input PCG, its non-uniformly distributed 3D points do not hold explicit connections between each other, making it difficult to examine the spatial dependency in the 3D neighborhood.…”

Section: Introductionmentioning

confidence: 99%

Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression

Wang¹,

Ding²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

This study develops a unified Point Cloud Geometry (PCG) compression method through Sparse Tensor Processing (STP) based multiscale representation of voxelized PCG, dubbed as the SparsePCGC. Applying the STP reduces the complexity significantly because it only performs the convolutions centered at Most-Probable Positively-Occupied Voxels (MP-POV). And the multiscale representation facilitates us to compress scale-wise MP-POVs progressively. The overall compression efficiency highly depends on the approximation accuracy of occupancy probability of each MP-POV, e.g., p MP-POV . Thus, we design the Sparse Convolution based Neural Networks (SparseCNN) consisting of sparse convolutions and voxel re-sampling to extensively exploit priors. We then develop the SparseCNN based Occupancy Probability Approximation (SOPA) model to estimate the p MP-POV s in a single-stage manner only using the cross-scale prior or in multi-stage by step-wisely utilizing autoregressive neighbors. Besides, we also suggest the SparseCNN based Local Neighborhood Embedding (SLNE) to characterize the local spatial variations as the feature attribute to improve the SOPA. Our unified approach shows the state-of-art performance in both lossless and lossy compression modes across a variety of datasets including the dense PCGs (8iVFB, Owlii) and the sparse LiDAR PCGs (KITTI, Ford) when compared with the MPEG G-PCC and other popular learning-based compression schemes. Furthermore, the proposed method presents lightweight complexity due to point-wise computation, and tiny storage desire because of model sharing across all scales. We make all materials publicly accessible at https://github.com/NJUVISION/SparsePCGC for reproducible research.

show abstract

Intra Prediction and Mode Coding in VVC

Cited by 82 publications

References 24 publications

High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation

High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation

Versatile Video Coding Standard: A Review from Coding Tools to Consumers Deployment

Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression

Contact Info

Product

Resources

About