Coding Prior-enhanced Dual Conditioning branches are designed to jointly model compressed video and coding prior conditions, where coding priors including residuals and motion vectors provide complementary structural and motion guidance during the diffusion denoising process.
Abstract
Perceptual quality enhancement of severely compressed videos remains challenging due to complex artifact patterns and substantial information loss. Recent diffusion models have demonstrated strong generative capability for visual restoration, but directly applying them to compressed video often ignores compression degradation characteristics and may introduce structure-inconsistent hallucinations. To address this issue, this paper presents a diffusion-based compressed video enhancement method, named DiffCVE. Coding Prior-enhanced Dual Conditioning (CPDC) branches are designed to jointly model compressed video and coding prior conditions, where coding priors including residuals and motion vectors provide complementary structural and motion guidance during the diffusion denoising process. To make the diffusion process aware of compression severity, a Compression Degradation Semantic Prompting (CDSP) mechanism is introduced to leverage QP-conditioned textual prompts together with LoRA fine-tuning. In addition, a Coding Prior-guided Weighted Fusion (CPWF) module is incorporated into the VAE decoder to fuse VAE encoder and coding prior encoder features with QP-predicted weights. Extensive experiments demonstrate the effectiveness of the proposed method in improving perceptual quality, especially under severe compression settings. The project page with enhanced video demonstrations is available at https://wqmaker.github.io/projects/DiffCVE/.
DiffVC-ONE, a diffusion-based generative video compression framework built on a one-step Video Diffusion Transformer, is proposed and a Unified Unidirectional Latent Compressor that uses a shared model to efficiently and uniformly compress compact latent slices is introduced.
Compressed video typically suffers from degraded visual quality due to artifacts such as blurring, blocking effects, and the attenuation of high-frequency details. These distortions make it challenging to accurately restore fine textures using conventional enhancement approaches that rely mainly on spatial domain information, as such methods lack effective modeling of high-frequency components degraded during compression. To address the above limitation, this paper proposes a frequency-aware compressed video quality enhancement framework that improves visual quality by adaptively enhancing high-frequency details and texture structures. The proposed method utilizes multiple consecutive frames and introduces a spatio-temporal feature alignment module to generate aligned features. A multi-scale high-frequency feature extraction strategy is then applied to capture fine details at different scales. Furthermore, an adaptive enhancement mechanism with spatial gating and high-frequency component weighting is proposed to selectively refine high-frequency details and suppress unnecessary enhancement. The frequency-enhanced features are then integrated with aligned features through a gated fusion strategy. Finally, the proposed quality enhancement module predicts a residual map, which is added to the center frame of the input sequence to produce the enhanced output. Experimental results demonstrate that the proposed method effectively reduces compression artifacts and enhances perceptual detail quality compared to existing approaches.
High-Compression videos suffer from severe distortions, among which degradation in person regions has the greatest impact on viewers’ immersive experience. Existing quality enhancement techniques usually focus on overall image denoising or super-resolution, often overlooking the crucial recovery of fine structures in these essential person regions. To address these challenges, the research introduces a novel framework titled Person Region Restoration Driven by Perceptual Fidelity (PRRDPF), which combines long-range dependency features with perceptual structure loss for enhanced generative restoration. Specifically, first, the research constructs a high-fidelity distorted person-region dataset via a closed-loop degradation pipeline, addressing the lack of paired datasets. Secondly, a Temporal Gated Fusion (TGF) block is designed to use gated convolutions for selectively recovering high-frequency features while capturing local and global dependencies. Finally, a Structural Similarity Index Measure (SSIM)-based dynamic weighted adversarial loss is proposed to prioritize the restoration of visual texture details. Experimental results validate that PRRDPF significantly outperforms the best models in Peak Signal-to-Noise Ratio (PSNR), SSIM, and Learned Perceptual Image Patch Similarity (LPIPS), effectively mitigating artifacts and enhancing clarity in person visuals. This framework presents a promising approach for intelligent video coding integrated with generative artificial intelligence and holds significant potential for practical applications.
Linyun Liu, Li Yu, Jiaxin Zeng et al.· IEEE Signal Processing Lette...· 0 citations
This work introduces the GenVC, a compression-oriented video diffusion model built on a video diffusion model trained from scratch for compression, and realizes this model directly in pixel space with a global-to-local hierarchy that recovers fine spatio-temporal details, enabling high-quality generative reconstruction from compressed representations.
Naifu Xue, Zhaoyang Jia, Haosen Li et al.· 0 citations
The latest video coding standard, H.266/VVC, has demonstrated significant improvements in compression efficiency compared to H.265/HEVC. Despite its advanced coding techniques, H.266/VVC still faces challenges in meeting the increasing demand for higher perceptual quality and enhanced compression performance. To address these limitations, we propose MDFI (Multi-Domain Features Integration), a compressed video quality enhancement approach that features a novel Frame-Prediction Feature Transform (FPFT) module to process prediction information. Moreover, MDFI integrates a multi-domain feature fusion strategy that effectively combines spatiotemporal characteristics, cross-frequency representations, and compressed-domain prediction information to enhance decoded video quality. Additionally, we introduce a comprehensive dataset that encompasses uncompressed video sequences, corresponding reconstructed versions at multiple QP levels, and predicted frames generated from H.266/VVC compressed bitstreams, providing essential resources for developing and benchmarking video enhancement approaches. Extensive experiments demonstrate that our MDFI approach achieves superior performance to state-of-the-art methods in both objective metrics and visual quality, effectively mitigating video compression artifacts. The code is available at: https://github.com/dangdinh17/MDFI.git.
Sang NguyenQuang, Hieu Bui Minh, Dang BuiDinh et al.· IEEE transactions on consume...· 0 citations