研究人员推出了一种新颖的基于扩散的方法DiffCVE，用于提升严重压缩视频的感知质量。该方法整合了残差和运动矢量等编码先验来指导扩散去噪过程，并使用一种压缩退化语义提示机制来考虑压缩的严重程度。此外，还将一个编码先验引导的加权融合模块集成到VAE解码器中以改进特征集成。另外，还提出了一种用于压缩视频盲质量提升的新方法，该方法提取细粒度的多尺度退化表示，并采用顺序推理策略根据压缩级别自适应地调整处理，显著提高了性能并减少了推理时间。
AI
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 compres…
arXiv:2607.07195v1 Announce Type: new 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 re…
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 compres…
arXiv:2511.16137v2 Announce Type: replace Abstract: Existing studies on quality enhancement for compressed video (QECV) predominantly rely on known quantization parameters (QPs), training separate enhancement models for each QP setting, which are referred to as non-blind methods.…
arXiv:2607.04606v1 Announce Type: cross Abstract: This report presents our solutions to the QoMEX 2026 Grand Challenge on Video Quality Assessment for Asymmetric Encoded Videos, comprising a full-reference (FR) model, CompressedVQA-AEV-FR, and a no-reference (NR) model, Compresse…
