RECORD
Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction
Computer Vision and Pattern Recognition · Submitted 15 Jun 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Comprehensive experimental results demonstrate our proposed C2F video compression framework equipped with the new hyperprior-guided mode prediction methods achieves the state-of-the-art performance on HEVC, UVG and MCL-JCV datasets.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
The previous deep video compression approaches only use the single scale motion compensation strategy and rarely adopt the mode prediction technique from the traditional standards like H.264/H.265 for both motion and residual compression. In this work, we first propose a coarse-to-fine (C2F) deep video compression framework for better motion compensation, in which we perform motion estimation, compression and compensation twice in a coarse to fine manner. Our C2F framework can achieve better motion compensation results without significantly increasing bit costs. Observing hyperprior information (i.e., the mean and variance values) from the hyperprior networks contains discriminant statistical information of different patches, we also propose two efficient hyperprior-guided mode prediction methods. Specifically, using hyperprior information as the input, we propose two mode prediction networks to respectively predict the optimal block resolutions for better motion coding and decide whether to skip residual information from each block for better residual coding without introducing additional bit cost while bringing negligible extra computation cost. Comprehensive experimental results demonstrate our proposed C2F video compression framework equipped with the new hyperprior-guided mode prediction methods achieves the state-of-the-art performance on HEVC, UVG and MCL-JCV datasets.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | The previous deep video compression approaches only use the single scale motion compensation strategy and rarely adopt the mode prediction technique from the traditional standards like H.264/H.265 for both motion and residual compression. | gap 0.61 | 0.04 | 0.02 | asserted 1.00 |
| s1 | In this work, we first propose a coarse-to-fine (C2F) deep video compression framework for better motion compensation, in which we perform motion estimation, compression and compensation twice in a coarse to fine manner. | contribution 0.68 | 0.92 | 0.08 | asserted 0.97 |
| s2 | Our C2F framework can achieve better motion compensation results without significantly increasing bit costs. | result 0.95 | 0.92 | 0.18 | asserted 0.83 |
| s3 | Observing hyperprior information (i.e., the mean and variance values) from the hyperprior networks contains discriminant statistical information of different patches, we also propose two efficient hyperprior-guided mode prediction methods. | contribution 0.86 | 0.84 | 0.05 | asserted 0.97 |
| s4 | Specifically, using hyperprior information as the input, we propose two mode prediction networks to respectively predict the optimal block resolutions for better motion coding and decide whether to skip residual information from each block for better residual coding without introducing additional bit cost while bringing negligible extra computation cost. | method 0.89 | 0.95 | 0.07 | asserted 1.00 |
| s5 | Comprehensive experimental results demonstrate our proposed C2F video compression framework equipped with the new hyperprior-guided mode prediction methods achieves the state-of-the-art performance on HEVC, UVG and MCL-JCV datasets. | result 1.00 | 0.96 | 0.90 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
The previous deep video compression approaches only use the single scale motion compensation strategy and rarely adopt the mode prediction technique from the traditional standards like H.264/H.265 for both motion and residual compression. In this work, we first propose a coarse-to-fine (C2F) deep video compression framework for better motion compensation, in which we perform motion estimation, compression and compensation twice in a coarse to fine manner. Our C2F framework can achieve better motion compensation results without significantly increasing bit costs. Observing hyperprior information (i.e., the mean and variance values) from the hyperprior networks contains discriminant statistical information of different patches, we also propose two efficient hyperprior-guided mode prediction methods. Specifically, using hyperprior information as the input, we propose two mode prediction networks to respectively predict the optimal block resolutions for better motion coding and decide whether to skip residual information from each block for better residual coding without introducing additional bit cost while bringing negligible extra computation cost. Comprehensive experimental results demonstrate our proposed C2F video compression framework equipped with the new hyperprior-guided mode prediction methods achieves the state-of-the-art performance on HEVC, UVG and MCL-JCV datasets.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites
Uses the method or tool of 1 paper
-
In order to minimize the influence of the video length mismatch between the training sequence and the testing sequence, we additionally adopt the random shift and different distortion weight strategies as suggested in [ref] .
Neural Video Compression using GANs for Detail Synthesis and Propagation · Experimental Setup · 0.99
Cites as background 1 paper
-
Recently, a few learning-based image compression [ref] and video compression [ref] methods have achieved promising compression performance.
Neural Video Compression using GANs for Detail Synthesis and Propagation · Image and Video Compression · 0.84
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.