Advanced Learning-Based Inter Prediction for Future Video Coding

• URL: http://arxiv.org/abs/2411.15759v1
• Date: Sun, 24 Nov 2024 08:47:00 GMT
• Title: Advanced Learning-Based Inter Prediction for Future Video Coding
• Authors: Yanchen Zhao, Wenhong Duan, Chuanmin Jia, Shanshe Wang, Siwei Ma,
• Abstract summary: The paper proposes a low complexity learning-based inter prediction (LLIP) method to replace the traditional INTERPF. LLIP enhances the filtering process by leveraging a lightweight neural network model, where parameters can be exported for efficient inference. Ultimately, we replace the traditional handcraft filtering parameters in INTERPF with the learned optimal filtering parameters.
• Score: 46.4999280984859
• License:
• Abstract: In the fourth generation Audio Video coding Standard (AVS4), the Inter Prediction Filter (INTERPF) reduces discontinuities between prediction and adjacent reconstructed pixels in inter prediction. The paper proposes a low complexity learning-based inter prediction (LLIP) method to replace the traditional INTERPF. LLIP enhances the filtering process by leveraging a lightweight neural network model, where parameters can be exported for efficient inference. Specifically, we extract pixels and coordinates utilized by the traditional INTERPF to form the training dataset. Subsequently, we export the weights and biases of the trained neural network model and implement the inference process without any third-party dependency, enabling seamless integration into video codec without relying on Libtorch, thus achieving faster inference speed. Ultimately, we replace the traditional handcraft filtering parameters in INTERPF with the learned optimal filtering parameters. This practical solution makes the combination of deep learning encoding tools with traditional video encoding schemes more efficient. Experimental results show that our approach achieves 0.01%, 0.31%, and 0.25% coding gain for the Y, U, and V components under the random access (RA) configuration on average.

Related papers

• In-Loop Filtering via Trained Look-Up Tables [45.6756570330982]
  In-loop filtering (ILF) is a key technology for removing the artifacts in image/video coding standards. We propose an efficient and practical in-loop filtering scheme by adopting the Look-up Table (LUT) Experimental results show that the ultrafast, very fast, and fast mode of the proposed method achieves on average 0.13%/0.34%/0.51%, and 0.10%/0.27%/0.39% BD-rate reduction.
  arXiv  Detail & Related papers  (2024-07-15T17:25:42Z)
• LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation [64.34935748707673]
  Recent deep neural networks (DNNs) have made impressive progress in performance by introducing learned data priors. We propose a novel method of Learning Resampling (termed LeRF) which takes advantage of both the structural priors learned by DNNs and the locally continuous assumption. LeRF assigns spatially varying resampling functions to input image pixels and learns to predict the shapes of these resampling functions with a neural network.
  arXiv  Detail & Related papers  (2024-07-13T16:09:45Z)
• Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler [103.97487121678276]
  Filter pruning simultaneously accelerates the computation and reduces the memory overhead of CNNs. We propose a novel Knowledge-driven Differential Filter Sampler(KDFS) with Masked Filter Modeling(MFM) framework for filter pruning.
  arXiv  Detail & Related papers  (2023-07-01T02:28:41Z)
• Progressive Fourier Neural Representation for Sequential Video Compilation [75.43041679717376]
  Motivated by continual learning, this work investigates how to accumulate and transfer neural implicit representations for multiple complex video data over sequential encoding sessions. We propose a novel method, Progressive Fourier Neural Representation (PFNR), that aims to find an adaptive and compact sub-module in Fourier space to encode videos in each training session. We validate our PFNR method on the UVG8/17 and DAVIS50 video sequence benchmarks and achieve impressive performance gains over strong continual learning baselines.
  arXiv  Detail & Related papers  (2023-06-20T06:02:19Z)
• Attention-based Feature Compression for CNN Inference Offloading in Edge Computing [93.67044879636093]
  This paper studies the computational offloading of CNN inference in device-edge co-inference systems. We propose a novel autoencoder-based CNN architecture (AECNN) for effective feature extraction at end-device. Experiments show that AECNN can compress the intermediate data by more than 256x with only about 4% accuracy loss.
  arXiv  Detail & Related papers  (2022-11-24T18:10:01Z)
• Complexity Reduction of Learned In-Loop Filtering in Video Coding [12.06039429078762]
  In video coding, in-loop filters are applied on reconstructed video frames to enhance their perceptual quality, before storing the frames for output. The proposed method uses a novel combination of sparsity and structured pruning for complexity reduction of learned in-loop filters.
  arXiv  Detail & Related papers  (2022-03-16T14:34:41Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• End-to-end Neural Video Coding Using a Compound Spatiotemporal Representation [33.54844063875569]
  We propose a hybrid motion compensation (HMC) method that adaptively combines the predictions generated by two approaches. Specifically, we generate a compoundtemporal representation (STR) through a recurrent information aggregation (RIA) module. We further design a one-to-many decoder pipeline to generate multiple predictions from the CSTR, including vector-based resampling, adaptive kernel-based resampling, compensation mode selection maps and texture enhancements.
  arXiv  Detail & Related papers  (2021-08-05T19:43:32Z)
• Improved CNN-based Learning of Interpolation Filters for Low-Complexity Inter Prediction in Video Coding [5.46121027847413]
  This paper introduces a novel explainable neural network-based inter-prediction scheme. A novel training framework enables each network branch to resemble a specific fractional shift. When implemented in the context of the Versatile Video Coding (VVC) test model, 0.77%, 1.27% and 2.25% BD-rate savings can be achieved.
  arXiv  Detail & Related papers  (2021-06-16T16:48:01Z)
• Interpreting CNN for Low Complexity Learned Sub-pixel Motion Compensation in Video Coding [16.381904711953947]
  A novel neural network-based tool is presented which improves the complexity of reference samples needed for fractional precision compensation motion. When the approach is implemented in the Versatile Video Coding (VVC) test model, up to 4.5% BD-rate saving for individual sequences is achieved. The complexity learned is significantly reduced compared to the application of full neural network.
  arXiv  Detail & Related papers  (2020-06-11T13:10:20Z)

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.