用语义信息优化视频压缩，让重要细节更清晰。
SCENE: Semantic-aware Codec Enhancement with Neural Embeddings
- 将视觉语言模型的语义嵌入融入轻量卷积网络，优先保护关键区域。
- 在高分辨率数据集上，MS-SSIM和VMAF指标均优于基线方法。
- 无需改动现有编码流程，可实时运行，适合部署到真实系统。
标准视频编码器产生的压缩伪影会降低主观质量。本文提出一种轻量级、语义感知的预处理框架，通过选择性修复这些失真来提升感知保真度。方法将视觉语言模型生成的语义嵌入整合进高效的卷积架构中，优先保留具有感知重要性的结构。模型采用可微分的编码器代理进行端到端训练，能有效缓解多种标准编码器的伪影，且无需修改现有视频流水线。推理时丢弃编码器代理，SCENE作为独立预处理器运行，实现实时性能。在高分辨率基准测试中，该方法在客观（MS-SSIM）和主观（VMAF）指标上均优于基线，尤其在显著区域的细节纹理保留上表现突出。结果表明，语义引导的、编码器感知的预处理是增强压缩视频流的有效方法。
原文摘要 · Abstract (English)
Compression artifacts from standard video codecs often degrade perceptual quality. We propose a lightweight, semantic-aware pre-processing framework that enhances perceptual fidelity by selectively addressing these distortions. Our method integrates semantic embeddings from a vision-language model into an efficient convolutional architecture, prioritizing the preservation of perceptually significant structures. The model is trained end-to-end with a differentiable codec proxy, enabling it to mitigate artifacts from various standard codecs without modifying the existing video pipeline. During inference, the codec proxy is discarded, and SCENE operates as a standalone pre-processor, enabling real-time performance. Experiments on high-resolution benchmarks show improved performance over baselines in both objective (MS-SSIM) and perceptual (VMAF) metrics, with notable gains in preserving detailed textures within salient regions. Our results show that semantic-guided, codec-aware pre-processing is an effective approach for enhancing compressed video streams.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。