Extending Neural P-frame Codecs for B-frame Coding
- URL: http://arxiv.org/abs/2104.00531v1
- Date: Tue, 30 Mar 2021 21:25:35 GMT
- Title: Extending Neural P-frame Codecs for B-frame Coding
- Authors: Reza Pourreza and Taco S Cohen
- Abstract summary: Our B-frame solution is based on the existing P-frame methods.
Our results show that using the proposed method with an existing P-frame can lead to 28.5%saving in bit-rate on the UVG dataset.
- Score: 15.102346715690755
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: While most neural video codecs address P-frame coding (predicting each frame
from past ones), in this paper we address B-frame compression (predicting
frames using both past and future reference frames). Our B-frame solution is
based on the existing P-frame methods. As a result, B-frame coding capability
can easily be added to an existing neural codec. The basic idea of our B-frame
coding method is to interpolate the two reference frames to generate a single
reference frame and then use it together with an existing P-frame codec to
encode the input B-frame. Our studies show that the interpolated frame is a
much better reference for the P-frame codec compared to using the previous
frame as is usually done. Our results show that using the proposed method with
an existing P-frame codec can lead to 28.5%saving in bit-rate on the UVG
dataset compared to the P-frame codec while generating the same video quality.
Related papers
- UCVC: A Unified Contextual Video Compression Framework with Joint
P-frame and B-frame Coding [29.44234507064189]
This paper presents a learned video compression method in response to video compression track of the 6th Challenge on Learned Image Compression (CLIC)
We propose a unified contextual video compression framework (UCVC) for joint P-frame and B-frame coding.
arXiv Detail & Related papers (2024-02-02T10:25:39Z) - IBVC: Interpolation-driven B-frame Video Compression [68.18440522300536]
B-frame video compression aims to adopt bi-directional motion estimation and motion compensation (MEMC) coding for middle frame reconstruction.
Previous learned approaches often directly extend neural P-frame codecs to B-frame relying on bi-directional optical-flow estimation.
We propose a simple yet effective structure called Interpolation-B-frame Video Compression (IBVC) to address these issues.
arXiv Detail & Related papers (2023-09-25T02:45:51Z) - FrameRS: A Video Frame Compression Model Composed by Self supervised
Video Frame Reconstructor and Key Frame Selector [9.896415488558036]
We present frame reconstruction model: FrameRS. It consists self-supervised video frame reconstructor and key frame selector.
The frame reconstructor, FrameMAE, is developed by adapting the principles of the Masked Autoencoder for Images (MAE) for video context.
The key frame selector, Frame Selector, is built on CNN architecture.
arXiv Detail & Related papers (2023-09-16T19:30:05Z) - Butterfly: Multiple Reference Frames Feature Propagation Mechanism for
Neural Video Compression [17.073251238499314]
We present a more reasonable multi-reference frames propagation mechanism for neural video compression.
Our method can significantly outperform the previous state-of-the-art (SOTA)
Our neural dataset can achieve -7.6% save on HEVC Class D when compared with our base single-reference frame model.
arXiv Detail & Related papers (2023-03-06T08:19:15Z) - Advancing Learned Video Compression with In-loop Frame Prediction [177.67218448278143]
In this paper, we propose an Advanced Learned Video Compression (ALVC) approach with the in-loop frame prediction module.
The predicted frame can serve as a better reference than the previously compressed frame, and therefore it benefits the compression performance.
The experiments show the state-of-the-art performance of our ALVC approach in learned video compression.
arXiv Detail & Related papers (2022-11-13T19:53:14Z) - B-CANF: Adaptive B-frame Coding with Conditional Augmented Normalizing
Flows [11.574465203875342]
This work introduces a novel B-frame coding framework, termed B-CANF, that exploits conditional augmented normalizing flows for B-frame coding.
B-CANF additionally features two novel elements: frame-type adaptive coding and B*-frames.
arXiv Detail & Related papers (2022-09-05T05:28:19Z) - TTVFI: Learning Trajectory-Aware Transformer for Video Frame
Interpolation [50.49396123016185]
Video frame (VFI) aims to synthesize an intermediate frame between two consecutive frames.
We propose a novel Trajectory-aware Transformer for Video Frame Interpolation (TTVFI)
Our method outperforms other state-of-the-art methods in four widely-used VFI benchmarks.
arXiv Detail & Related papers (2022-07-19T03:37:49Z) - Asymmetric Bilateral Motion Estimation for Video Frame Interpolation [50.44508853885882]
We propose a novel video frame algorithm based on asymmetric bilateral motion estimation (ABME)
We predict symmetric bilateral motion fields to interpolate an anchor frame.
We estimate asymmetric bilateral motions fields from the anchor frame to the input frames.
Third, we use the asymmetric fields to warp the input frames backward and reconstruct the intermediate frame.
arXiv Detail & Related papers (2021-08-15T21:11:35Z) - Learning for Video Compression with Recurrent Auto-Encoder and Recurrent
Probability Model [164.7489982837475]
This paper proposes a Recurrent Learned Video Compression (RLVC) approach with the Recurrent Auto-Encoder (RAE) and Recurrent Probability Model ( RPM)
The RAE employs recurrent cells in both the encoder and decoder to exploit the temporal correlation among video frames.
Our approach achieves the state-of-the-art learned video compression performance in terms of both PSNR and MS-SSIM.
arXiv Detail & Related papers (2020-06-24T08:46:33Z) - M-LVC: Multiple Frames Prediction for Learned Video Compression [111.50760486258993]
We propose an end-to-end learned video compression scheme for low-latency scenarios.
In our scheme, the motion vector (MV) field is calculated between the current frame and the previous one.
Experimental results show that the proposed method outperforms the existing learned video compression methods for low-latency mode.
arXiv Detail & Related papers (2020-04-21T20:42:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.