SCENE: Semantic-aware Codec Enhancement with Neural Embeddings

TL;DR

SCENE is a lightweight, semantic-aware pre-processing framework that enhances perceptual quality of compressed videos by integrating semantic embeddings, improving fidelity without altering existing codecs, and enabling real-time operation.

Contribution

The paper introduces a novel semantic-aware pre-processing method that leverages neural embeddings to improve perceptual quality of compressed videos without changing standard codecs.

Findings

Improved MS-SSIM and VMAF scores on high-resolution benchmarks.

Enhanced preservation of detailed textures in salient regions.

Real-time performance as a standalone pre-processor.

Abstract

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.