Rate-distortion Cost Research Articles

High efficiency deep image compression via channel-wise scale adaptive latent representation learning

Recent learning based neural image compression methods have achieved impressive rate–distortion (RD) performance via the sophisticated context entropy model, which performs well in capturing the spatial correlations of latent features. However, due to the dependency on the adjacent or distant decoded features, existing methods require an inefficient serial processing structure, which significantly limits its practicability. Instead of pursuing computationally expensive entropy estimation, we propose to reduce the spatial redundancy via the channel-wise scale adaptive latent representation learning, whose entropy coding is spatially context-free and parallelizable. Specifically, the proposed encoder adaptively determines the scale of the latent features via a learnable binary mask, which is optimized with the RD cost. In this way, lower-scale latent representation will be allocated to the channels with higher spatial redundancy, which consumes fewer bits and vice versa. The downscaled latent features could be well recovered with a lightweight inter-channel upconversion module in the decoder. To compensate for the entropy estimation performance degradation, we further develop an inter-scale hyperprior entropy model, which supports the high efficiency parallel encoding/decoding within each scale of the latent features. Extensive experiments are conducted to illustrate the efficacy of the proposed method. Our method achieves bitrate savings of 18.23%, 19.36%, and 27.04% over HEVC Intra, along with decoding speeds that are 46 times, 48 times, and 51 times faster than the baseline method on the Kodak, Tecnick, and CLIC datasets, respectively.

Fast Depth Map Coding Algorithm for 3D-HEVC Based on Gradient Boosting Machine

Three-Dimensional High-Efficiency Video Coding (3D-HEVC) has been extensively researched due to its efficient compression and deep image representation, but encoding complexity continues to pose a difficulty. This is mainly attributed to redundancy in the coding unit (CU) recursive partitioning process and rate–distortion (RD) cost calculation, resulting in a complex encoding process. Therefore, enhancing encoding efficiency and reducing redundant computations are key objectives for optimizing 3D-HEVC. This paper introduces a fast-encoding method for 3D-HEVC, comprising an adaptive CU partitioning algorithm and a rapid rate–distortion-optimization (RDO) algorithm. Based on the ALV features extracted from each coding unit, a Gradient Boosting Machine (GBM) model is constructed to obtain the corresponding CU thresholds. These thresholds are compared with the ALV to further decide whether to continue dividing the coding unit. The RDO algorithm is used to optimize the RD cost calculation process, selecting the optimal prediction mode as much as possible. The simulation results show that this method saves 52.49% of complexity while ensuring good video quality.

Divide-and-conquer-based RDO-free CU Partitioning for 8K Video Compression

8K (7689×4320) ultra-high definition (UHD) videos are growing popular with the improvement of human visual experience demand. Therefore, the compression of 8K UHD videos has become a top priority in the third-generation audio video coding standard (AVS3). However, as an important part of the coding standard promotion, the real-time hardware implementation for AVS3-based 8K UHD video intra coding is severely hindered, especially in the coding unit (CU) partition stage. To break through the limitation, this article proposes a divide-and-conquer-based rate-distortion-optimization-free (RDO-free) CU partitioning algorithm for efficient hardware implementation. Aimed at the complex CU partition in AVS3, we separately design a lightweight optimization for original partitioning rules to improve division efficiency and a decision tree-based RDO-free CU decision framework to eliminate the latency caused by the waiting for rate-distortion cost calculation in RDO strategy. Afterward, a divide-and-conquer-based hardware-friendly gradient difference calculating approach is devised to accelerate the learning feature extracting speed. To ensure that the proposed algorithm is sufficient to support the real-time CU partition for 8K videos, we also develop a hardware architecture based on FPGA. Experimental results illustrate that the software coding performance of our algorithm is significantly ahead of the efficient implementation uAVS3e for AVS3 and the reference software HM-16.20 for High Efficiency Video Coding (HEVC), even though there is 9.96% loss on BD-Rate Y. Considering its importance for the hardware implementation of AVS3-based 8K real-time encoder, the coding loss is acceptable. Moreover, the hardware simulation results on VU440 FPGA with Vivado 2019 show that our algorithm can support 61.12 frames per second (fps) CU partition for 8K UHD videos with only 0.00%, 0.00%, 1.01%, and 7.78% consumption of BRAM_18K, DSP48E, FF, and LUT, respectively. Additionally, with dual-path parallelism, 122.24 fps also can be implemented with controllable resource utilization, which achieves the state-of-the-art performance.

Adaptive HEVC Video Steganography With High Performance Based on Attention-Net and PU Partition Modes

With the increasing popularity of digital video, video steganography has become a hot research topic in the field of covert communication and privacy protection. The existing prediction unit (PU) based video steganography often tends to result in large bit rate increase, which is also easily noticeable to the steganography analyst. To solve this problem, an adaptive steganography for HEVC video based on attention-net and PU partition modes is proposed. First, the distortion of modified PUs is analyzed from the perspective of rate distortion optimization at the group of pictures (GOP) level, and we find that modifying PU will lead to distortion accumulation and abnormal bitrate increase. Therefore, an adaptive distortion function based on the improved rate distortion cost is designed, and the embedding distortion is minimized by using Syndrome-Trellis Code (STC) steganography coding. Meanwhile, a super-resolution convolutional neural network with non-local sparse attention-net filter is proposed to replace the in-loop filter in HEVC to reconstruct the reference frame, thereby reducing the bitrate cost and improving the visual quality of stego-video. Experimental results show that the proposed algorithm can achieve superior perceptual quality and bitrate performance comparing with the sate-of-the-art works.

An anti-steganalysis adaptive steganography for HEVC video based on PU partition modes

Calibration-based steganalysis methods are a fatal threat to current HEVC steganography algorithms. The current steganography algorithms based on prediction unit (PU) still lack resistance to this type of steganalysis. The reason is that the improvements in HEVC codec provide more potential steganographic space as well as introduce more detectable distortion. Therefore, a HEVC video steganography method that has resistance to PU shift-based steganalysis is proposed in this paper. First, the PU shift phenomenon that exists in PU-based steganography is introduced. Then the existing calibration-based steganalysis method is enhanced. According to the encoding rules of HEVC, the distortion cost function according to the difference of rate distortion cost (RD cost) during recompression is designed, which aims to obtain better resistance to calibration-based steganalysis. Experimental results demonstrate that the steganography algorithm designed in this paper provides excellent resistance ability for calibration-based steganalysis.

Efficient CU Decision Algorithm for VVC 3D Video Depth Map Using GLCM and Extra Trees

The new generation of 3D video is an international frontier research hotspot. However, the large amount of data and high complexity are core problems to be solved urgently in 3D video coding. The latest generation of video coding standard versatile video coding (VVC) adopts the quad-tree with nested multi-type tree (QTMT) partition structure, and the coding efficiency is much higher than other coding standards. However, the current research work undertaken for VVC is less for 3D video. In light of this context, we propose a fast coding unit (CU) decision algorithm based on the gray level co-occurrence matrix (GLCM) and Extra trees for the characteristics of the depth map in 3D video. In the first stage, we introduce an edge detection algorithm using GLCM to classify the CU in the depth map into smooth and complex edge blocks based on the extracted features. Subsequently, the extracted features from the CUs, classified as complex edge blocks in the first stage, are fed into the constructed Extra trees model to make a fast decision on the partition type of that CU and avoid calculating unnecessary rate-distortion cost. Experimental results show that the overall algorithm can effectively reduce the coding time by 36.27–51.98%, while the Bjøntegaard delta bit rate (BDBR) is only increased by 0.24% on average which is negligible, all reflecting the superior performance of our method. Moreover, our algorithm can effectively ensure video quality while saving much encoding time compared with other algorithms.

Complexity-Efficient Dependent Quantization for Versatile Video Coding

The dependent quantization (DQ) technique in Versatile Video Coding (VVC) provides high compression efficiency, but it suffers from much computation, which is not preferred in practical applications. In this context, we propose a complexity-efficient dependent quantization structure employing a machine learning-based DQ start position prediction and a simplified trellis structure. Firstly, the proposed DQ start position is decided by a binary classifier which finds an appropriate location to start the DQ process. To further reduce the processing time of the binary classification, we also set up a precondition with a learned preset threshold which can reduce the number of coefficients subjected to the classifier. Based on our statistical analysis showing that under certain conditions some branches of the trellis structure are not necessary to check, we also design a branch pruning method and a removal scheme of all-zero coefficient group checking to simplify the DQ trellis structure. Our proposed complexity-efficient DQ has much fewer calculations of rate-distortion costs. Our experimental results show that it can reduce the computational complexity of the DQ process with nearly no performance loss of Bjontegaard delta bit rate (BDBR) irrespective of the all intra or the random access configurations.

Block-Adaptive Point Cloud Attribute Coding With Region-Aware Optimized Transform

Block-based compression scheme shows remarkable success in image and video coding. However, existing tree-type block partition methods usually divide point clouds into clusters with few or disjoint points due to the irregular sampling, which is adverse for the subsequent transform to exploit the local region correlation. Moreover, the widely-used optimal transform, e.g., Discrete Cosine Transform (DCT), is deduced with the assumption of the specified probability model. Thus these transforms cannot adequately conform to diverse statistical characteristics of point cloud attributes. To address the above two problems, we propose a block-adaptive codec with the optimized transform for point cloud attribute compression, including Progressive Clustering (PC) for block partition and Region-Aware Signal Modeling (RASM) for transform. PC is designed via the split-and-merge strategy. In the splitting phase, over-segmented clusters are obtained by iteratively searching the nearest neighbors to maintain the spatial continuity of points in one cluster. In the merging step, blocks are determined by merging over-segmented clusters under the guidance of minimizing texture complexity, which adjusts block sizes to adapt to texture variation. RASM adaptively captures the color correlations to respond to diverse statistical characteristics by optimizing the overall Rate-Distortion (RD) cost. Then, the optimal transform bases are obtained via the eigen-decomposition of the color correlation representation with respect to the Gaussian Markov Random Field, where input colors are obtained considering the linear relationship between geometry and color variations. The linear coefficients also need to be encoded to combine geometry to reconstruct the transform bases at the decoder in the same way as the encoder. Particularly, we accelerate the RASM by constraining the independent relationship between signals in the local region, which hardly influences RD performance. Extensive experiments not only indicate the effectiveness of PC and RASM but also show the significant RD gains achieved by our approach compared with several state-of-the-art platforms.

Hybrid Strategies for Efficient Intra Prediction in Spatial SHVC

With multi-layer encoding and Inter-layer prediction, Spatial Scalable High Efficiency Video Coding (SSHVC) has extremely high coding complexity. It is very crucial to speed up its coding to promote widespread and cost-effective SSHVC applications. Specifically, we first reveal that the average RD cost of Inter-layer Reference (ILR) mode is different from that of Intra mode, but they both follow the Gaussian distribution. Based on this discovery, we apply the classic Gaussian Mixture Model and Expectation Maximization to determine whether ILR mode is the best mode thus skipping Intra mode. Second, when coding units (CUs) in enhancement layer use Intra mode, it indicates very simple texture is presented. We investigate their Directional Mode (DM) distribution, and divide all DMs into three classes, and then develop different methods with respect to classes to progressively predict the best DMs. Third, by jointly considering rate distortion costs, residual coefficients and neighboring CUs, we propose to employ the Conditional Random Fields model to early terminate depth selection. Experimental results demonstrate that the proposed algorithm can significantly improve coding speed with negligible coding efficiency losses.

Accelerating QTMT-based CU partition and intra mode decision for versatile video coding

The H.266/VVC achieves about 50% bitrate saving compared to its predecessor H.265/HEVC at the expense of exponentially increased computational complexity. The most efficient but complex technique for H.266/VVC intra frame coding is the QuadTree with a nested Multi-type Tree encoding structure (QTMT), which usually requires traversing the Rate-Distortion (R-D) cost of each partition and each mode for the best option. To alleviate such computational burden while preserving the coding efficiency as much as possible, this paper develops a multi-feature guided Fast CU Partition (FCP) and Laplacian guided Fast Mode Selection (FMS) to accelerate the intra QTMT decision together. For FCP, we regard the CU partition as a classification problem and adopt the Support Vector Machine (SVM) for its low-complexity implementation; after evaluating the contribution of a set of features, three representative features of video textures are selected and used to train the SVM model. Additionally, an advanced technique is applied by adopting a soft decision in SVM for a more flexible trade-off between the complexity and R-D performance. For FMS, we utilize the Laplace operator to determine the most probable directions of the current CU and skip half of the candidate modes for runtime saving. Experimental results demonstrate that the proposed FCP reduces the encoding time of H.266/VVC by 51.03% with 1.65% Bjøntegaard Delta Bit-Rate (BDBR) increase; the proposed FMS reduces the encoding time by 12.68% with 0.09% BDBR loss. Their direct combination and advanced combination finally lead to 54.84% encoding time reduction with 1.74% BDBR increase and 40.39% encoding time reduction with 1.33% BDBR increase, respectively, outperforming state-of-the-art approaches significantly.

Fast Rate-Distortion Optimization for Depth Maps in 3-D Video Coding

To ensure the fidelity of virtual views, rate-distortion optimization (RDO) criterion for the 3D extension of the High Efficiency Video Coding (3D-HEVC) is well designed, in which the synthesized view distortion (SVD) is introduced to derive the rate-distortion (RD) cost. To obtain accurate SVDs, the rendering operation is employed which demands a fairly high computational complexity. To address this problem, a fast RDO method for depth maps is proposed, which checks the RD cost during its calculation process. Specifically, given a coding mode, the RD cost is composed of several cumulative items. If the accumulated RD cost is equal to or exceeds the minimum RD cost of previously coded modes, it will not be necessary to continue the RD cost calculation for the mode. To reduce the encoding complexity, existing methods usually aim at reducing the number of tested modes or block partitions. To the best of our knowledge, it is the first time that the latent redundant complexity in the RD cost calculation is investigated and removed. Experimental results demonstrate that, compared with the 3D-HEVC reference software, the proposed method can save 28.1% of depth coding time with a small coding gain (0.04% BD-rate saving). An additional test is designed to evaluate four typical fast coding methods with/without the proposed method. Extensive results verify that the proposed method can be seamlessly combined with the state-of-the-art methods.

Lookahead Search-Based Low-Complexity Multi-Type Tree Pruning Method for Versatile Video Coding (VVC) Intra Coding

The latest versatile video coding (VVC) introduces some novel techniques such as quadtree with nested multi-type tree (QTMT), multiple transform selection (MTS) and multiple reference line (MRL). These tools improve compression efficiency compared with the previous standard H.265/HEVC, but they suffer from very high computational complexity. One of the most time-consuming parts of VVC intra coding is the coding tree unit (CTU) structure decision. In this paper, we propose a low-complexity multi-type tree (MT) pruning method for VVC intra coding. This method consists of lookahead search and MT pruning. The lookahead search process is performed to derive the approximate rate-distortion (RD) cost of each MT node at depth 2 or 3. Subsequently, the improbable MT nodes are pruned by different strategies under different cost errors. These strategies are designed according to the priority of the node. Experimental results show that the overall proposed algorithm can achieve 47.15% time saving with only 0.93% Bjøntegaard delta bit rate (BDBR) increase over natural scene sequences, and 45.39% time saving with 1.55% BDBR increase over screen content sequences, compared with the VVC reference software VTM 10.0. Such results demonstrate that our method achieves a good trade-off between computational complexity and compression quality compared to recent methods.

LOW COMPLEXITY HEVC SCALABLE ENCODER BASED ON FSS ALGORITHM

High efficiency video coding (HEVC) provides compressed video bit streams with good quality video that offers an extension of its kind-Scalable extension of high efficiency video coding (SHVC). SHVC offers delivery of compressed video bit streams over various types of networks with broader scalability. Mode decision and motion search in standard HEVC is more exhaustive and complex, and it is even more complex in the HEVC scalable extension. The encoder time increases due to the computational complexity in SHVC to find the best mode in the search algorithm. To overcome this, a forward-looking step search (FSS) algorithm is proposed to offer less computational complexity with acceptable coding efficiency. The FSS algorithm searches for the optimal matching block by fixing nine points around the assumed center point. The optimal block is determined by forward-looking each point that has minimal rate distortion cost (RDC). The simulation results show that the algorithm works better with a 0.5% increase in the peak signal-to-noise ratio (PSNR) and an encoder time savings of 21.16% with the standard SHVC SHM software.

Partition Map Prediction for Fast Block Partitioning in VVC Intra-Frame Coding

The Versatile Video Coding (VVC) standard introduces a block partitioning structure known as quadtree plus nested multi-type tree (QTMTT), which allows more flexible block partitioning compared to its predecessors, like High Efficiency Video Coding (HEVC). Meanwhile, the partition search (PS) process, which is to find out the best partitioning structure for optimizing the rate-distortion cost, becomes far more complicated for VVC than for HEVC. Also, the PS process in VVC reference software (VTM) is not friendly to hardware implementation. We propose a partition map prediction method for fast block partitioning in VVC intra-frame encoding. The proposed method may replace PS totally or be combined with PS partially, thereby achieving adjustable acceleration of the VTM intra-frame encoding. Different from the previous methods for fast block partitioning, we propose to represent a QTMTT-based block partitioning structure by a partition map, which consists of a quadtree (QT) depth map, several multi-type tree (MTT) depth maps, and several MTT direction maps. We then propose to predict the optimal partition map from the pixels through a convolutional neural network (CNN). We propose a CNN structure, known as Down-Up-CNN, for the partition map prediction, where the CNN structure emulates the recursive nature of the PS process. Moreover, we design a post-processing algorithm to adjust the network output partition map, so as to obtain a standard-compliant block partitioning structure. The post-processing algorithm may produce a partial partition tree as well; then based on the partial partition tree, the PS process is performed to obtain the full tree. Experimental results show that the proposed method achieves 1.61× to 8.64× encoding acceleration for the VTM-10.0 intra-frame encoder, with the ratio depending on how much PS is performed. Especially, when achieving 3.89× encoding acceleration, the compression efficiency loss is 2.77% in BD-rate, which is a better tradeoff than the previous methods.

Multitask Learning Based Intra-Mode Decision Framework for Versatile Video Coding

In mid-2020, the new international video coding standard, namely versatile video coding (VVC), was officially released by the Joint Video Expert Team (JVET). As its name indicates, the VVC enables a higher level of versatility with better compression performance compared to its predecessor, high-efficiency video coding (HEVC). VVC introduces several new coding tools like multiple reference lines (MRL) and matrix-weighted intra-prediction (MIP), along with several improvements on the block-based hybrid video coding scheme such as quatree with nested multi-type tree (QTMT) and finer-granularity intra-prediction modes (IPMs). Because finding the best encoding decisions is usually preceded by optimizing the rate distortion (RD) cost, introducing new coding tools or enhancing existing ones requires additional computations. In fact, the VVC is 31 times more complex than the HEVC. Therefore, this paper aims to reduce the computational complexity of the VVC. It establishes a large database for intra-prediction and proposes a multitask learning (MTL)-based intra-mode decision framework. Experimental results show that our proposal enables up to 30% of complexity reduction while slightly increasing the Bjontegaard bit rate (BD-BR).

Analysis of coding unit partitioning and complexity reduction at intra-prediction mode of HEVC

ABSTRACT The emerging trend of ultra-high definition (4 K, UHD) video services necessitates coding efficiency, which is much higher than H.264. High-Efficiency Video Coding (HEVC) has been designed with the intention of drastically reducing the bit rate without compromising the video quality. The key feature is the introduction of a larger block structure with flexible block sizes from 64 × 64 to 8 × 8 samples. The enhanced feature has imposed higher complexity, specifically at the intra-prediction mode level of HEVC. The proposed research work has presented a novel hybrid approach to reducing the number of candidate Coding Units (CU) passing through irrelevant partition patterns and time-consuming iterative Rate-Distortion (RD) cost estimation process. The hybrid approach is implemented in two steps. In the first step gradient evaluation is performed and the CU is categorized as homogeneous or non-homogeneous. In the second step Early Termination is adopted by using machine learning for partitioning non-homogeneous CU. As the number of candidate Coding Units undergoing the time-consuming RD process is reduced by using the two-step hybrid approach, the proposed approach proves to be the best of its kind. The reduction in the number of candidate units undergoing the RD process reduces the complexity of the intra-prediction process. Encoding time is the measure of complexity and the proposed hybrid approach reduces the encoding time by an average of 36% compared with the HEVC reference model and also by an average of 26% as compared with the previous work. The Peak Signal to Noise Ratio (PSNR) reduced by an average of 0.1% indicates a slight reduction in the encoded image quality. The proposed approach significantly reduced the encoding time without affecting the RD performance of the encoder. The image quality is not compromised substantially when considering the improvement in the encoding time and the reduction in the complexity at an intra-prediction level.

Fast Decision Algorithm of CU Size for HEVC Intra-Prediction Based on a Kernel Fuzzy SVM Classifier

High Efficiency Video Coding (HEVC) achieves a significant improvement in compression efficiency at the cost of extremely high computational complexity. Therefore, large-scale and wide deployment applications, especially mobile real-time video applications under low-latency and power-constrained conditions, are more challenging. In order to solve the above problems, a fast decision method for intra-coding unit size based on a new fuzzy support vector machine classifier is proposed in this paper. The relationship between the depth levels of coding units is accurately expressed by defining the cost evaluation criteria of texture and non-texture rate-distortion cost. The fuzzy support vector machine is improved by using the information entropy measure to solve the negative impact of data noise and the outliers problem. The proposed method includes three stages: the optimal coded depth level “0” early decision, coding unit depth early skip, and optimal coding unit early terminate. In order to further improve the rate-distortion complexity optimization performance, more feature vectors are introduced, including features such as space complexity, the relationship between coding unit depths, and rate-distortion cost. The experimental results showed that, compared with the HEVC reference test model HM16.5, the proposed algorithm can reduce the encoding time of various test video sequences by more than 53.24% on average, while the Bjontegaard Delta Bit Rate (BDBR) only increases by 0.82%. In addition, the proposed algorithm is better than the existing algorithms in terms of comprehensively reducing the computational complexity and maintaining the rate-distortion performance.

Low-Complexity Multiple Transform Selection Combining Multi-Type Tree Partition Algorithm for Versatile Video Coding.

Despite the fact that Versatile Video Coding (VVC) achieves a superior coding performance to High-Efficiency Video Coding (HEVC), it takes a lot of time to encode video sequences due to the high computational complexity of the tools. Among these tools, Multiple Transform Selection (MTS) require the best of several transforms to be obtained using the Rate-Distortion Optimization (RDO) process, which increases the time spent video encoding, meaning that VVC is not suited to real-time sensor application networks. In this paper, a low-complexity multiple transform selection, combined with the multi-type tree partition algorithm, is proposed to address the above issue. First, to skip the MTS process, we introduce a method to estimate the Rate-Distortion (RD) cost of the last Coding Unit (CU) based on the relationship between the RD costs of transform candidates and the correlation between Sub-Coding Units’ (sub-CUs’) information entropy under binary splitting. When the sum of the RD costs of sub-CUs is greater than or equal to their parent CU, the RD checking of MTS will be skipped. Second, we make full use of the coding information of neighboring CUs to terminate MTS early. The experimental results show that, compared with the VVC, the proposed method achieves a 26.40% reduction in time, with a 0.13% increase in Bjøontegaard Delta Bitrate (BDBR).

Communication-Efficient Federated Learning via Predictive Coding

Federated learning can enable remote workers to collaboratively train a shared machine learning model while allowing training data to be kept locally. In the use case of wireless mobile devices, the communication overhead is a critical bottleneck due to limited power and bandwidth. Prior work has utilized various data compression tools such as quantization and sparsification to reduce the overhead. In this paper, we propose a predictive coding based compression scheme for federated learning. The scheme has shared prediction functions among all devices and allows each worker to transmit a compressed residual vector derived from the reference. In each communication round, we select the predictor and quantizer based on the rate–distortion cost, and further reduce the redundancy with entropy coding. Extensive simulations reveal that the communication cost can be reduced up to 99% with even better learning performance when compared with other baseline methods.

RDNet: Rate–Distortion-Based Coding Unit Partition Network for Intra-Prediction

High efficiency video coding (HEVC) has been finalized as the most widely utilized video coding standard, jointly developed by ITU-T, VCEG, and MPEG. In HEVC, the quad-tree structure of the coding unit partition is one of the most substantial modules and provides significant coding gains following huge coding time. In this paper, a rate–distortion-based coding unit partition network (RDNet) is proposed to make partition decisions based on the statistical features. RDNet is composed of a prediction sub-network and a target sub-network, where the prediction sub-network is used to predict the CU partition modes of the intra-prediction and the target sub-network is designed to optimize the network parameters by evaluating the rate–distortion cost, respectively. To balance the prediction accuracy and the rate–distortion loss, a parameter-exchanging strategy is applied to control the parameters’ sharing between two networks. Experimental results prove that our model can reduce the encoding time of HEVC by 55.83~71.72% with an efficient BD-BR of 2.876~3.347%, and the ablation study evaluates the ability of our strategy on balancing the trade-off between coding accuracy and inference speed.