PulseAugur
EN
LIVE 08:33:06

New AI methods enhance compressed video quality and assessment · 5 sources tracked

By PulseAugur Editorial · [5 sources] ·

Researchers have introduced DiffCVE, a novel diffusion-based method for enhancing the perceptual quality of severely compressed videos. This approach incorporates coding priors like residuals and motion vectors to guide the diffusion denoising process and uses a Compression Degradation Semantic Prompting mechanism to account for compression severity. Additionally, a Coding Prior-guided Weighted Fusion module is integrated into the VAE decoder for improved feature integration. Separately, a new method for blind quality enhancement of compressed video has been proposed, which extracts fine-grained, multi-scale degradation representations and employs a sequential inference strategy to adaptively adjust processing based on compression levels, significantly improving performance and reducing inference time. AI

IMPACT These advancements in video enhancement and quality assessment could lead to improved streaming services, more efficient video compression, and better tools for analyzing video content.

RANK_REASON The cluster consists of multiple research papers detailing new methods for video enhancement and quality assessment.

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 5 sources. How we write summaries →

New AI methods enhance compressed video quality and assessment · 5 sources tracked

COVERAGE [5]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    DiffCVE: Diffusion-based Compressed Video Enhancement

    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…

  2. arXiv cs.CV TIER_1 English(EN) · Wenqiang Xiao, Wenzhuo Ma, Junxi Zhang, Zhenzhong Chen ·

    DiffCVE: Diffusion-based Compressed Video Enhancement

    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…

  3. arXiv cs.CV TIER_1 English(EN) · Zhenzhong Chen ·

    DiffCVE: Diffusion-based Compressed Video Enhancement

    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…

  4. arXiv cs.CV TIER_1 English(EN) · Li Yu, Yingbo Zhao, Shiyu Wu, Siyue Yu, Moncef Gabbouj, Qingshan Liu ·

    Blind Quality Enhancement of Compressed Video via Fine-Grained Degradation-Guided Sequential Inference

    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.…

  5. arXiv cs.CV TIER_1 English(EN) · Wei Sun, Xingwei Liu, Dandan Zhu, Xiangyang Zhu, Weixia Zhang, Guangtao Zhai ·

    CompressedVQA-AEV: Full-Reference and No-Reference Quality Assessment Models for Asymmetric Encoded Videos

    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…

RELATED ENTITIES

RELATED TOPICS