Recent studies on video rate control (RC) have introduced accurate and high performance methods but have not explored the optimal RC solution. The optimal solution is crucial for improving RC methods and providing labels for supervised learning. To find approximate optimal RC solutions within a limited time, we are the first to propose a reinforcement learning based search method for finding approximate optimal RC solutions within a limited time. Specifically, the RC problem for a video is first modeled as a Markov decision process (MDP). Then, with the MDP model, we develop a search method based on the deep Q-network method, which consists of exploration and exploitation steps. During exploration, an agent is created, consisting of two multilayer perceptrons and a replay memory, and trained within the MDP to estimate the value function, while superior RC solutions are recorded throughout the training process. After training, RC solution is estimated by the trained agent using the value function and a greedy strategy during the exploitation step. Finally, the approximate optimal RC solution is determined based on the RC solutions from both two steps. In addition, the time complexity of proposed method is controllable, specifically,$O(m n)$where$m$denotes the number of training epoch. Experimental results show that the bit-rate error and compression quality of the solutions found by proposed method approach the optimal solutions, with differences of only less than 0.005% and 0.399%, respectively, and are achieved in a significantly shorter time compared to the brute force search.

Inter prediction is a fundamental component of modern video coding, where the quality of reference frames critically affects motion compensation accuracy and overall compression efficiency. However, relying solely on reconstructed low-temporal-layer frames imposes significant limitations, as these frames often suffer from compression artifacts that degrade prediction quality. To overcome this limitation, we propose a Local-Global spatiotemporal context modeling-based virtual reference frame generation network (LGCM-Net) that synthesizes high-quality reference frames based on reconstructed frames, as shown in Fig. 1. The proposed network integrates hierarchical feature extraction with long-range dependency modeling, where QP-conditioned modulation is applied to shallow features to adapt them to quantization-induced quality variations, enabling temporally and structurally consistent reference generation closely aligned with the to-be-coded frame. Moreover, a coarse-to-fine multi-stage optical flow refinement mechanism is employed to progressively enhance motion accuracy, and a residual refiner further compensates remaining motion estimation errors and reconstruction artifacts to deliver a more accurate final prediction. The proposed method achieves$5.37 \%, 9.96 \%$, and 9.91% BD-rate reduction under the Random Access configuration in VVC reference Software (VTM-11.0_nnvc-10.0 w/o NN Coding tools) for the$\mathrm{Y}, \mathrm{U}$, and V components, respectively.

In this paper, we propose a feed-forward framework (Fig. 1) for human video compression based on 3D generative reconstruction. Recent surveys [1], [2] highlight the need for more efficient and semantically aligned solutions. Our approach disentangles video content into complementary structural and motion layers: the structural layer encodes regularized texture from a single frame, while the motion layer leverages the SMPL-X prior to represent complex dynamics with a compact set of pose and shape parameters. A hierarchical coding scheme exploits the heterogeneity of these representations for improved efficiency. After decoding, a feed-forward 3D reconstruction pipeline with facial feature extraction is employed, in which a multimodal transformer and a Gaussian head synthesize parametric cues that are fused with motion signals for accurate animation and high-fidelity rendering. Experiments show over$1000 \times$compression while preserving structural and semantic fidelity. The method consistently outperforms strong baselines (especially at$0.04-0.1 \text{kbpp})$, with significant gains in rate-distortion, FVD, and perceptual quality, as well as robust generalization across identities and scenes.

Neural network-based in-loop filtering significantly enhances video compression efficiency. However, high computational complexity hinders their deployment in real-time and ultra-high-definition scenarios. To address this, we propose a lightweight CNN-based in-loop filter for the luma component. In terms of model design, we utilize a U-Net-like architecture to learn the residual signal, incorporating depthwise separable 3 × 3 convolutions and 1 × 1 convolutions to reduce computational complexity, which results in a low complexity of only$37.707 \text{kMACs} /$pixel. For deployment optimization, we implement memory linearization to improve cache efficiency and combine blocked matrix multiplication with SIMD to maximize parallelism, ensuring cross-platform compatibility without third-party libraries. Experimental results on AVS4 EVM-0.9 (All-Intra) on a CPU platform show that the proposed method achieves BD-rate reductions of$1.36 \%, 0.35 \%$, and 0.34% for$\mathrm{Y}, \mathrm{U}$, and V components, respectively. Furthermore, the optimizations lead to a 91.5% reduction in decoding time, resulting in a decoding complexity of 7757% compared to the anchor.

Video post-processing can significantly enhance compressed video quality. Traditional methods are mostly based on handcrafted designs, such as deblocking and deringing algorithms, which rely on fixed heuristic rules and exhibit limited flexibility and adaptability. In recent years, with the rapid development of deep learning, Neural Network-based (NN-based) video post-processing methods have demonstrated remarkable coding performance. Among these, Transformer-based or multi-frame joint enhancement methods have improved reconstruction quality but still heavily depend on the prediction of known pixels, making it difficult to effectively restore high-frequency texture information lost due to the lossy compression. In contrast, diffusion models leverage their powerful generative priors and progressive denoising mechanisms to synthesize more natural and realistic high-frequency details, providing a promising solution for video post-processing. Inspired by recent advancements in conditional generative modeling, we propose a diffusion-based post-processing filter. The design incorporates a quantization parameter adaptive module and a block-based inference strategy with overlapping blocks to balance visual quality and efficiency. Experimental results demonstrate that the proposed method achieves significant improvements in both subjective and objective quality on the VTM-11.0.

Since the introduction of hierarchical picture prediction structure in the advanced video coding (AVC), the hierarchical coding structure (HCS) has been widely adopted and continuously improved in video coding standards. Correspondingly, the HCS-based bit allocation methods in rate control have also emerged endlessly. Considering that pictures in higher temporal levels (TLs) of HCS usually refer to pictures in lower TLs, most methods tend to allocate more bits to pictures in lower TLs. However, these methods do not fully consider the correlation of picture quality in different TLs, which leads to the bit allocation waste and the coding performance degradation. To address this issue, we propose a fast bit allocation refinement method that can adapt to different video rate control approaches. Fig. 1 shows the overall framework of the proposed method. In general, our method is to appropriately adjust the bit allocation of pictures in lower TLs according to the relationship between the quality of pictures in different TLs. Specifically, based on the hyperbolic rate-distortion (RD) model and initial allocated bits, the quality of picture in higher TLs is first predicted and then used to estimate the quality of picture in lower TLs. Subsequently, the bits of picture in lower TLs are derived using estimated quality and its RD model. Finally, the final allocated bits of picture in lower TLs are adjusted by comparing the estimated and initial allocated bits. Experimental results show that our method can improve the coding performance of different rate control methods without introducing latency and encoding complexity.

Intra prediction is a crucial component of hybrid video coding framework due to its remarkable ability to reduce spatial redundancy in video signals. Unlike the single-mode based intra prediction in HEVC and VVC, intra fusion prediction methods, that combine the results of multiple angular prediction modes, were newly adopted by Enhanced Compression Model (ECM). However, intra fusion prediction over-relies on local spatial correlations and neglects potential texture similarities in non-adjacent regions. To overcome these limitations and elevate the accuracy of luma intra prediction, a Recurrent Intra Prediction Mode (RIPM) is proposed in this paper, which is composed of two sub-modules, i.e., Recurrent Intra Merge Mode (RIMM) and Recurrent Block Vector Substitution Module (RBVSM). RIMM utilizes the recurrent spatial texture information of the adjacent and non-adjacent spaces for adaptive mode derivation and prediction within the intra fusion prediction framework. RBVSM is a sophisticated mechanism for adaptive prediction mode selection and weight assignment during intra fusion prediction, resulting in enhanced coding performance with minimal impact on computational complexity. The proposed method, implemented on top of ECM-12.0, demonstrates a 0.095% BD-rate gain for the luma component under All Intra configuration, with negligible complexity increase. Currently, RIPM is under study in Exploration Experiments (EE) for ECM in JVET.

This paper elaborates the binary bin distribution of each syntax element in AVS3. The overall syntax elements in AVS3 can be divided into Context-Modeled(CM) Bin, Bypass(BPS) Bin, Weighted Context-Modeled(WCM) Bin. A comprehensive and quantitative analysis on these bitstreams are conducted and the result is shown in Fig. 1. Moreover, Fig. 2 illustrates the distribution of CM Bin, BPS Bin, and WCM Bin across various resolutions and QPs. The analysis reveals insightful correlations between the types of binary symbols and syntax elements within the AVS3 bitstream. Through this analysis, we aim to contribute to the implementation of AVS3 codecs.

This paper propose a Image Coding for Machine (ICM) framework with Visual-Language Mimic Feature Learning (VLM-ICM). VLM-ICM decouples the position and semantic information into language modality and extracts universal features from the input image. Language, inherently more semantically compact, helps reduce the bitrate. Meanwhile, the universal features in VLM-ICM, guided by the language at the decoder side, allow for flexible domain adaptation, thereby enhancing versatility and practicality.

The Decoder-side Secondary Transform Derivation (DSTD) method has been adopted by the exploration software of the fourth generation Audio Video coding Standard (AVS4), Exploration Video Model (EVM). Although DSTD can significantly improve the coding performance, it increases the encoding complexity simultaneously. To reduce the encoding complexity of DSTD, three enhanced DSTD methods are proposed in this paper, which consists of Deleting Mode Optimization (DMO), Intra Mode Dependent Optimization (IMDO) and Interleaved Intra Mode Dependent Optimization (IIMDO). The process of DMO is similar to that of the original DSTD method, but all the contents related to diagonal flipping have been removed. IMDO divides intra prediction modes into three areas based on the angle of the intra prediction mode, as shown in Fig. 1. Each area will correspondingly reduce a secondary transform type. IIMDO divides intra prediction modes into four areas, as shown in Fig. 2. The experimental results demonstrate that the proposed methods can effectively reduce the encoding complexity with negligible coding performance loss. The first enhanced method, Deleting Mode Optimization, has been adopted by EVM.

Screen content is an important category of video. The statistical distribution of pixels in screen content exhibits substantial differences compared to camera-captured video, leading to different compression needs and challenges. Hitherto, most Screen Content Coding (SCC) tools are designed for block-based hybrid coding frameworks, which may not be suitable for emerging wavelet-based and learning-based coding frameworks. Consequently, a plug-and-play SCC tool independent of coding frameworks is lacking in the current video coding landscape. In this paper, an out-loop coding method, Frequency-based Adaptive Pixel Correction (FAPC), is proposed to improve the SCC performance for arbitrary codecs. First, a True Color Value (TCV) table is established based on the most frequently occurring pixel values. Then, the reconstructed pixels are corrected according to the TCV table. To realize precise pixel correction, an adaptive threshold derivation method is meticulously designed to control the pixel correction process. Furthermore, an inheritance coding strategy is proposed to reduce the overhead of parameter transmission. The proposed method has been integrated into three different coding frameworks. Simulation results demonstrate that the proposed method can achieve 10.66%, 3.55% and 10.67% luma component BD-BR gains on the three coding frameworks, respectively. These results prove the superiority and universality of the proposed method.

Cloud gaming is an advanced form of Internet service that necessitates local terminals to decode within limited resources and time latency. Super-Resolution (SR) techniques are often employed on these terminals as an efficient way to reduce the required bit-rate bandwidth for cloud gaming. However, insufficient attention has been paid to SR of compressed game video content. Most SR networks amplify block artifacts and ringing effects in decoded frames while ignoring edge details of game content, leading to unsatisfactory reconstruction results. In this paper, we propose a novel lightweight network called Coding Prior-Guided Super-Resolution (CPGSR) to address the SR challenges in compressed game video content. First, we design a Compressed Domain Guided Block (CDGB) to extract features of different depths from coding priors, which are subsequently integrated with features from the U-net backbone. Then, a series of re-parameterization blocks are utilized for reconstruction. Ultimately, inspired by the quantization in video coding, we propose a partitioned focal frequency loss to effectively guide the model's focus on preserving high-frequency information. Extensive experiments demonstrate the advancement of our approach.

Logarithmic binary arithmetic coding (LBAC) is a entropy coding method first introduced in AVS2 and now used in the third generation of audio video coding standard (AVS3). While LBAC provides high coding efficiency, the data dependencies in AVS3 make it challenging to parallelize parsing syntax element. To enhance the throughput of AVS3 LBAC entropy decoding engine, a sophisticated hardware implementation architecture is meticulously designed in the paper. The proposed method decouples the bitstream decoding process into four distinct modules. To ensure the decoding efficiency and performance, an advanced parallel pipeline is carefully designed. Furthermore, we develop sub-branch state prediction mechanism and grouped decoding method to further improve the decoding efficiency. The proposed AVS3 entropy decoder has been implemented on the S10 FPGA System Board, and experimental results show that the proposed method could achieve real-time and seamless decoding efficiency for 8K AVS3 bitstreams, even at bitrates as high as 207.1Mbps.

This paper proposes a fast four-parameter Affine Motion Compensation (AMC) algorithm. As shown in Fig. 1, the translation Motion Vector (MV) is derived by reusing the AMC sub-block MV derivation method firstly, which is used to conduct translation pre-transform. Secondly, a coordinate system whose coordinate origin is located on its top-left control point is established for the transformed block. Finally, the geometric relationship between two control point motion vectors (CPMVs) of the transformed block can be described as follows,\begin{equation*}\delta = \left| {\left({m{v_{0x}} - m{v_{1x}}}\right) \times H - \left({m{v_{0y}} + m{v_{1y}}}\right) \times W} \right| = 0\tag{1}\end{equation*}

Intra prediction acts a significant role in removing the spatial redundancy in the hybrid coding framework. Versatile Video Coding (VVC) employs a set of angular intra modes to generate directional contents based on the linear projection hypothesis. However, the linear based predictor is not expressive enough for generating high-fidelity patterns with non-linear structure. To compensate for that, we propose a high-order intra prediction (HOIP) for future video coding in this paper. In particular, the HOIP is modeled by a quadratic extrapolation function. To be compatible with the present intra prediction mechanism, the quadratic function can be formulated by two angular intra modes. To reduce the encoding complexity, we further propose a search pruning strategy to find the most appropriate pair-wise modes, and it can be flexibly extended for higher coding performance. The extensive experimental results demonstrate the effectiveness of the proposed method. Up to 0.6% BD-rate saving is obtained with the moderate complexity increment.

Flexible coding unit partitioning such as quad-tree nested binary-tree and ternary-tree adopted by the emerging enhanced compression model (ECM) brings promising coding performance improvement. Meanwhile, the computational complexity increases dramatically, which may block the exploration and validation of new coding tools. This paper investigates a partition mode early pruning scheme via a fully connected network to reduce the encoding complexity for the ECM. In particular, we carefully select features and devise the fully connected network, which could seamlessly cooperate with the encoder, revealing promising learning and inference capability. Experimental results demonstrate that the proposed method achieves 15%~50% encoding time savings with moderate bit-rate increasing on the ECM, and the extra complexity regarding the fully connected network and feature extraction is negligible.

In-loop filter is a crucial module in video coding, which can improve both subjective and object quality of reconstructed videos. In this paper, a new sample-based classification method is first proposed using features extracted from different stages of the existing in-loop filter process. Based on this method, an adaptive three-layer Quad-tree Based Sample Refinement Filter (QSRF) algorithm is designed to further improve the coding efficiency. Experimental results show that the proposed QSRF algorithm achieves 0.39%, 0.77% and 0.70% BD-rate savings for random access, lowdelay B and lowdelay P configurations compared to AVS3 reference software, respectively. Moreover, the proposed method can also improve visual quality of reconstructed videos significantly.

In the Versatile Video Coding (VVC) standard, adaptive loop filter (ALF), including Geometry transformation-based Adaptive Loop Filter (GALF) and Cross Component Adaptive Loop Filter (CCALF), plays an essential role in reducing compression artifacts. However, it also has high coding complexity and requires many picture buffer accesses in the encoder that will increase external memory access and is unfriendly to the software and hardware design. Therefore, we propose an optimized ALF framework, including the parallel design of GALF and CCALF, the adaptive parameter decision of GALF, and one-pass CCALF scheme by effectively estimating the CCALF filtering distortion without conducting filter operation. Compared to VTM-8.0, the proposed method can reduce the picture buffer access from 152 to 1 and achieve roughly 25% time-savings of the ALF module with negligible coding performance change under RA configuration. Some of the proposed methods have been adopted in the VVC reference software.