SCENE: Semantic-aware Codec Enhancement with Neural Embeddings
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917233198891008 |
|---|---|
| author | Lin, Han-Yu Chen, Li-Wei Lee, Hung-Shin |
| author_facet | Lin, Han-Yu Chen, Li-Wei Lee, Hung-Shin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22189 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SCENE: Semantic-aware Codec Enhancement with Neural Embeddings Lin, Han-Yu Chen, Li-Wei Lee, Hung-Shin Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Multimedia 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. |
| title | SCENE: Semantic-aware Codec Enhancement with Neural Embeddings |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Multimedia |
| url | https://arxiv.org/abs/2601.22189 |