Neural Video Compression has emerged in recent years, with condition-based frameworks outperforming traditional codecs. However, most existing methods rely solely on the previous frame's features to predict temporal context, leading to two critical issues. First, the short reference window misses long-term dependencies and fine texture details. Second, propagating only feature-level information accumulates errors over frames, causing prediction inaccuracies and loss of subtle textures. To address these, we propose the Long-term Spatio-Temporal Enhanced Context (L-STEC) method. We first extend the reference chain with LSTM to capture long-term dependencies. We then incorporate warped spatial context from the pixel domain, fusing spatio-temporal information through a multi-receptive field network to better preserve reference details. Experimental results show that L-STEC significantly improves compression by enriching contextual information, achieving 37.01% bitrate savings in PSNR and 31.65% in MS-SSIM compared to DCVC-TCM, outperforming both VTM-17.0 and DCVC-FM and establishing new state-of-the-art performance.

Recent advances in end-to-end video compression have shown promising results owing to their unified end-to-end learning optimization. However, such generalized frameworks often lack content-specific adaptation, leading to suboptimal compression performance. To address this, this paper proposes a content adaptive based motion alignment framework that improves performance by adapting encoding strategies to diverse content characteristics. Specifically, we first introduce a two-stage flow-guided deformable warping mechanism that refines motion compensation with coarse-to-fine offset prediction and mask modulation, enabling precise feature alignment. Second, we propose a multi-reference quality aware strategy that adjusts distortion weights based on reference quality, and applies it to hierarchical training to reduce error propagation. Third, we integrate a training-free module that downsamples frames by motion magnitude and resolution to obtain smooth motion estimation. Experimental results on standard test datasets demonstrate that our framework CAMA achieves significant improvements over state-of-the-art Neural Video Compression models, achieving a 24.95% BD-rate (PSNR) savings over our baseline model DCVC-TCM, while also outperforming reproduced DCVC-DC and traditional codec HM-16.25.

Recently, neural image compression (NIC) has made remarkable progress. Two key parts of NIC are the encoder-decoder and the entropy model. For the encoder-decoder, a larger effective receptive field (ERF) means a stronger transformation ability. Existing methods usually enlarge the ERF at the expense of complexity, which is intolerable. To address this issue, we propose a multi-scale depthwise separable dilated convolution (MSDSDC) to build the encoder-decoder. Specifically, we first construct a depthwise separable dilated convolution (DSDC) by using the depthwise separable strategy in dilated convolution to reduce its complexity. Subsequently, multi-scale features extracted by three DSDCs with varying dilation rates are fused to expand the ERF of the encoder-decoder, consequently enhancing its transformation capability. Besides, we design a multi-distribution mixture entropy model (MDMEM) to further enhance the flexibility of latent representation probability modeling. The experimental results demonstrate that our proposed method achieves the best balance between rate-distortion performance and complexity.

In this paper, a flow-guided temporal-spatial network (FGTSN) is proposed to enhance the quality of HEVC compressed video. Specifically, we first employ a robust motion estimation subnet via trainable optical flow module to estimate the motion flow between the target frame and its adjacent frames, and these adjacent frames are pre-warped guided by the predicted motion flow. Then, a temporal encoder is proposed to fuse the related information between the target frame and its pre-warped frames. Finally, a quality enhancement subnet with multi-scale encoder-decoder structure is designed to generate high quality frame by training the network in a multi-supervised fashion. Experimental results show the superior performance of our proposed FGTSN method for the reconstruction quality of HEVC compressed frames, much better than the state-of-the-art quality enhancement methods. In addition, our FGTSN method can also effectively mitigate the quality fluctuation of adjacent frames.

In this paper, we propose a new HEVC in-loop filter based on a multi-channel long-short-term dependency residual network (MLSDRN). Inspired by the information storage and information update function of human memory cell, our MLSDRN introduces an update cell to adaptively store and select the long-term and short-term dependency information through an adaptive learning process. In addition, we leverage the block boundary information that recorded in the bit-streams to improve the filter performance, which also makes our MLSDRN to unequally treat the video content. Meanwhile, the multi-channel is introduced to solve the illumination discrepancy problem. We integrate the novel in-loop filter into HM reference software, and applying it to luma and chroma components, simulation results demonstrate that the proposed in-loop filter can save BD-rate reduction up to 15.9% with ALF off. For luma component, the novel in-loop filter achieves 6.0%, 8.1%, 7.4% BD-rate saving for all intra, low delay and random access configurations, respectively.