Technology Category
Computer Vision: Video Understanding & Activity AnalysisMachine Learning: Multimodal LearningSearch and Optimization: Learning to Search
Joint Video Enhancement with Deblurring, Super-Resolution, and Frame Interpolation Network
🤖 AI Summary
Video quality is often degraded by coupled factors—including blur, low resolution, and low frame rate—rendering conventional sequential enhancement methods inefficient and suboptimal. To address this, we propose an end-to-end joint video enhancement framework that, for the first time, unifies modeling of these three degradation types. Our approach introduces two core components: a Joint Deblurring and Super-Resolution (JDSR) module and a Three-Frame-Based Frame Interpolation (TFBFI) module, enabling holistic reconstruction of high-resolution, high-frame-rate, and blur-free video. Leveraging differentiable joint optimization, we overcome the performance and efficiency bottlenecks inherent in serial processing. Extensive experiments on public benchmarks demonstrate that our method significantly outperforms state-of-the-art sequential approaches: it achieves higher PSNR and SSIM, employs fewer model parameters, and enables faster inference—thereby validating the effectiveness and practicality of joint degradation modeling.
Technology Category
Application Category
📝 Abstract
Video quality is often severely degraded by multiple factors rather than a single factor. These low-quality videos can be restored to high-quality videos by sequentially performing appropriate video enhancement techniques. However, the sequential approach was inefficient and sub-optimal because most video enhancement approaches were designed without taking into account that multiple factors together degrade video quality. In this paper, we propose a new joint video enhancement method that mitigates multiple degradation factors simultaneously by resolving an integrated enhancement problem. Our proposed network, named DSFN, directly produces a high-resolution, high-frame-rate, and clear video from a low-resolution, low-frame-rate, and blurry video. In the DSFN, low-resolution and blurry input frames are enhanced by a joint deblurring and super-resolution (JDSR) module. Meanwhile, intermediate frames between input adjacent frames are interpolated by a triple-frame-based frame interpolation (TFBFI) module. The proper combination of the proposed modules of DSFN can achieve superior performance on the joint video enhancement task. Experimental results show that the proposed method outperforms other sequential state-of-the-art techniques on public datasets with a smaller network size and faster processing time.
Problem
Research questions and friction points this paper is trying to address.
Simultaneously address video degradation from multiple factors
Integrate deblurring, super-resolution, and frame interpolation jointly
Enhance low-quality videos to high-resolution, high-frame-rate outputs
Innovation
Methods, ideas, or system contributions that make the work stand out.
Joint deblurring and super-resolution module
Triple-frame-based frame interpolation
Simultaneous multi-factor video enhancement
🔎 Similar Papers
No similar papers found.
