Search papers, labs, and topics across Lattice.
This paper introduces DiffCVE, a novel method for enhancing the perceptual quality of severely compressed videos by leveraging diffusion models tailored to account for compression artifacts. By integrating Coding Prior-enhanced Dual Conditioning (CPDC) branches and a Compression Degradation Semantic Prompting (CDSP) mechanism, the approach effectively utilizes coding priors and contextual information to guide the diffusion denoising process. Extensive experiments reveal that DiffCVE significantly improves video quality, particularly in scenarios with high compression levels, outperforming existing techniques.
Severe video compression can lead to substantial quality loss, but DiffCVE effectively restores perceptual quality by intelligently harnessing coding priors and diffusion models.
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 compressed video often ignores compression degradation characteristics and may introduce structure-inconsistent hallucinations. To address this issue, this paper presents a diffusion-based compressed video enhancement method, named DiffCVE. Coding Prior-enhanced Dual Conditioning (CPDC) branches are designed to jointly model compressed video and coding prior conditions, where coding priors including residuals and motion vectors provide complementary structural and motion guidance during the diffusion denoising process. To make the diffusion process aware of compression severity, a Compression Degradation Semantic Prompting (CDSP) mechanism is introduced to leverage QP-conditioned textual prompts together with LoRA fine-tuning. In addition, a Coding Prior-guided Weighted Fusion (CPWF) module is incorporated into the VAE decoder to fuse VAE encoder and coding prior encoder features with QP-predicted weights. Extensive experiments demonstrate the effectiveness of the proposed method in improving perceptual quality, especially under severe compression settings. The project page with enhanced video demonstrations is available at https://wqmaker.github.io/projects/DiffCVE/.
